business-context-os

LLM wiki kit

First committed by walm00

Published in walm00/business-context-os. Publisher page

22 GitHub starsUpdated 2026-05-15

What it is

CLEAR Context OS is the maintenance layer your second brain never had: ownership boundaries enforced mechanically, staleness surfaced on a schedule, drift propagated across linked docs, a dispatcher that learns from your clicks. One source of truth per topic. Searchable. Task-aware.

— the description by walm00

AutoGineer overview, from the brain’s own files

CLEAR Context OS is a framework designed to solve the problem of silent context degradation in AI agents. By implementing a structured methodology called CLEAR (Contextual Ownership, Linking, Elimination, Alignment, Refinement), it provides a maintenance layer that manages knowledge through automated scheduling, ownership enforcement, and drift detection. It organizes information into specific zones—such as canonical data, wiki-based derivatives, and verbatim evidence—ensuring that agents always operate on the most accurate, source-of-truth-ranked information. The system includes a dispatcher for scheduled maintenance, a local dashboard for monitoring, and integration with Claude Code to facilitate onboarding and task-aware context retrieval.

How it works

Memory model: LLM wiki

AutoGineer overview, from the brain’s own files

The system organizes information into a folder hierarchy where the path itself acts as a trust signal for the LLM. It uses a dispatcher to run scheduled maintenance jobs that check for staleness, propagate updates across linked documents, and audit content health. New information is ingested through a routing process that places content into specific zones: canonical data for facts, wiki pages for operational knowledge, and collections for legal evidence. The system learns from user interactions to suggest fixes and uses frontmatter metadata to allow agents to filter and retrieve information efficiently without full-text scanning.

Folders
Folder	Role	Files
.claude	agent-config	193
.github	agent-config	6
docs	docs	68

The agent reads

docs/_bcos-framework/guides/folder-conventions.md evidence: CLAUDE.md
docs/_inbox/ evidence: README.md

The agent writes

docs/_inbox/ evidence: CLAUDE.md

Requirements

Works with: Claude Code, OpenCode

Set it up

This brain runs code automatically: 5 hooks (claude-code), 1 script. Review .claude/settings.json, install.sh before opening the folder in Claude Code. No step below turns a hook on for you.
- .claude/settings.json: bash "$CLAUDE_PROJECT_DIR/.claude/hooks/auto_save_session.sh"
- .claude/settings.json: bash "$CLAUDE_PROJECT_DIR/.claude/hooks/precompact_save.sh"
- .claude/settings.json: "$CLAUDE_PROJECT_DIR/.claude/bin/python3" "$CLAUDE_PROJECT_DIR/.claude/hooks/post_edit_frontmatter_check.py"
- .claude/settings.json: "$CLAUDE_PROJECT_DIR/.claude/bin/python3" "$CLAUDE_PROJECT_DIR/.claude/hooks/post_edit_frontmatter_check.py"
- .claude/settings.json: "$CLAUDE_PROJECT_DIR/.claude/bin/python3" "$CLAUDE_PROJECT_DIR/.claude/hooks/post_commit_context_check.py"
- install.sh: sh install.sh

Clone the repository at the commit AutoGineer scanned:

git clone https://github.com/walm00/business-context-os.git && cd business-context-os && git checkout 463568372f31f24fa6c01121c38f989845ca7c84

Claude Code reads CLAUDE.md from this folder automatically.
cd business-context-os && claude
AutoGineer scanned these files at commit 4635683.
First committed by walm00. Published in walm00/business-context-os. Licence: MIT License.

Usage

AutoGineer overview, from the brain’s own files

Automating the maintenance of project documentation and SOPs.
Providing AI agents with a reliable, freshness-aware knowledge base.
Managing ownership boundaries across large, multi-topic documentation sets.
Syncing and auditing context across linked documents to prevent drift.
Generating daily digests of system health and pending maintenance tasks.

“Install BCOS from https://github.com/walm00/business-context-os and walk me through onboarding.”: Claude clones the repository, sets up the environment, and guides the user through an interactive onboarding process to configure the context architecture.
“/context bundle market-report:write”: The agent retrieves a curated, freshness-aware package of context specifically relevant to writing a market report.
“Run the audit twice a week.”: The dispatcher updates the maintenance schedule to perform an audit of the knowledge base on a bi-weekly cadence.
“/wiki run https://stripe.com/docs/api”: The system fetches the URL, summarizes the content, and creates a cited wiki entry within the knowledge base.

Documentation by walm00

<h1 align="center">CLEAR Context OS</h1> Knowledge that maintains itself — so your AI doesn't act on what was true last month. <a href="#install">Install</a>  ·  <a href="#what-it-does">What it does</a>  ·  <a href="#the-wiki-zone">Wiki zone</a>  ·  <a href="#what-ships">What ships</a>  ·  <a href="docs/_bcos-framework/guides/getting-started.md">Getting Started</a> <img src="https://img.shields.io/badge/claude_code-ready-blueviolet" alt="Claude Code"> <img src="https://img.shields.io/badge/methodology-CLEAR-green" alt="CLEAR Methodology"> <img src="https://img.shields.io/badge/install-one_command-success" alt="One-command install"> <img src="https://img.shields.io/badge/skills-17-blue" alt="17 skills"> <img src="https://img.shields.io/badge/maintenance_jobs-12-orange" alt="12 maintenance jobs"> <img src="https://img.shields.io/badge/license-MIT-lightgrey" alt="MIT">

Your AI had perfect context — two weeks ago. Then your strategy shifted, three meetings redefined priorities, and the docs you wrote on Monday are wrong by Friday. CLEAR Context OS is the maintenance layer your second brain never had: ownership boundaries enforced mechanically, staleness surfaced on a schedule, drift propagated across linked docs, a dispatcher that learns from your clicks. One source of truth per topic. Searchable. Task-aware. Never silently stale.

Install

Easiest — let Claude do it. Open Claude Code in any directory and paste:

"Install BCOS from https://github.com/walm00/business-context-os and walk me through onboarding."

Claude clones the repo, picks the right install path for your platform (Windows/macOS/Linux), runs setup, and steps straight into onboarding. No prereq checks to debug — if something's missing, Claude resolves it interactively.

Or manually, two commands:

curl -fsSL https://raw.githubusercontent.com/walm00/business-context-os/main/install.sh -o /tmp/bcos-install.sh
bash /tmp/bcos-install.sh

(Requires bash, curl, and tar on PATH — fine on macOS/Linux and on Windows under WSL or Git Bash. Two steps instead of a single bash <(curl …) pipe so Claude Code's permission gate auto-approves both commands — you don't need to drop out to a terminal.)

Drop anything you already have — SOPs, brand docs, meeting notes, exports — into docs/_inbox/ (skip if you're starting fresh). Then open Claude Code in that repo and say:

"Launch BCOS onboarding."

That's the only prompt you need. Onboarding inspects your inbox, scans the rest of the repo, asks one Q&A round, and proposes the architecture for review. Works the same whether the repo is fresh or already full of context.

From zero to running

  INSTALL  →  DISCOVER  →  ALIGN  →  SCHEDULE  →  RUNNING

#	Step	What happens
1	Install	One bash line drops the framework into any repo
2	Discover	Claude scans your repo + any MCP you've connected (Drive, Notion, Slack, Gmail, your CRM — whatever's wired in) for existing context, plus anything you've dropped into `docs/_inbox/`
3	Align	One Q&A round — project type, key sources, ownership boundaries. Architecture drafted for your review
4	Schedule	Pick maintenance cadence in plain English: "audit twice a week", "dispatcher at 08:30", "deep daydream off"
5	Running	Daily digest. Local dashboard. `/context bundle <task>` ready. Context compounds from here — the system maintains itself.

Simple, guided, automatic. Claude walks you through each step — you review, you decide. Nothing deleted along the way — originals preserved or archived, never silently overwritten.

What it does

Stops context rot in three ways:

	What it does
Organize	Every doc declares what it owns. CLEAR boundaries prevent the same fact living in 5 places.
Maintain	Scheduled jobs check freshness, surface stale docs, propagate updates across linked content.
Use	`/context search` and `/context bundle <task>` give Claude curated, freshness-aware, source-of-truth-ranked context for the job at hand.

The folder tells the LLM what to trust. Claude reads the path before the content: docs/*.md = canonical, _planned/ = not yet real, _archive/ = history, _inbox/ = unprocessed, _collections/ = verbatim evidence, _wiki/ = explanatory. The hierarchy is the trust signal — fewer tokens spent re-deciding, no chance of treating an archived draft as today's truth.

docs/
├── *.md                  ← canonical data points (one source of truth per topic)
├── document-index.md     ← auto-generated TOC
├── current-state.md      ← what's true right now + what changed recently
├── table-of-context.md   ← high-level cluster map for orientation
├── _inbox/               ← drop zone — Claude triages on demand
├── _planned/             ← polished ideas, not yet real
├── _archive/             ← superseded — kept, not deleted
├── _collections/         ← verbatim evidence (invoices, contracts, transcripts)
│   └── <type>/_manifest.md   (each collection has a manifest)
├── _wiki/                ← derivative knowledge (how-tos, source summaries)
│   ├── pages/            ← user-authored explainers
│   ├── source-summary/   ← external captures with citation banners
│   ├── raw/              ← original artifacts (PDFs, HTML)
│   └── queue.md          ← URLs awaiting fetch
└── _bcos-framework/      ← framework docs — never user content
    ├── architecture/     ← 12 zone + system architecture docs
    ├── methodology/      ← 5 CLEAR + ownership + standards docs
    ├── patterns/         ← 8 project-type starting templates
    └── templates/        ← 15 frontmatter / schema / starter files

The wiki zone

Inspired by Karpathy's LLM Wiki approach — give the LLM a wiki of your knowledge, the way you'd brief a smart new hire.

Save anything to the wiki, from anywhere:

/wiki run https://stripe.com/docs/api          ← fetch a URL, summarize, cite
/wiki create from /Users/me/Downloads/spec.pdf ← extract a PDF, link to the binary
/wiki promote docs/_inbox/meeting-notes.md     ← turn an inbox capture into a wiki page

The wiki holds how-tos, runbooks, glossaries, source summaries, post-mortems, decision logs — derivative knowledge that explains and supports your canonical data points. Every page cites what it builds on. Stale pages surface automatically when their sources advance.

Wiki content is searchable alongside the rest of your context:

/context search "stripe billing"       ← cross-zone search, ranked by source-of-truth
/context bundle market-report:write    ← curated bundle for a specific task

The dashboard

A local cockpit at http://127.0.0.1:8091 that shows your system at a glance — no third-party services, no telemetry, no logins.

Image: BCOS dashboard cockpit — knowledge system status, things waiting on you, maintenance routine

python .claude/scripts/bcos-dashboard/run.py

Surface	What you see
Cockpit	One-line status (healthy / N waiting / heads-up). Per-job dot strip for every maintenance job (core BCOS + wiki zone).
Update	"Run full sync" button → `update.py` + CLAUDE.md drift review + auto-commit + push, with a live log drawer.
Schedules (`/settings/schedules`)	Per-job preset buttons (`daily`, `mon_wed_fri`, `weekly_mon`, `off`) + the global auto-commit toggle + auto-fix whitelist. Saves directly to `schedule-config.json`.
Run history (`/settings/runs`)	Last 20 dispatcher runs with filter chips (job / verdict / trigger).
File health (`/settings/files`)	Frontmatter / cross-reference / staleness findings with one-click fixes.

The dashboard is read-mostly: data flows from the dispatcher's diary, the schedule config, and the canonical context index. Writes (mark-done, schedule preset, auto-commit toggle, file fix) go through dedicated POST endpoints.

Requirements

Claude Code (desktop app, CLI, or web)
Python 3.8+ on PATH
bash (default macOS bash 3.2 is fine)

Updating

python .claude/scripts/update.py

Refreshes framework files only — skills, hooks, scripts, templates. Your docs/ and .private/ are never touched.

Maintenance

One scheduled task per repo. The dispatcher reads schedule-config.json, runs the jobs due today, writes one consolidated digest at docs/_inbox/daily-digest.md, and surfaces findings as one-click cards in the dashboard.

Image: BCOS maintenance schedule dispatcher — daily, weekly, monthly jobs flowing into the daily digest and dashboard cards

You can tune any of it in plain English:

"Run the audit twice a week." · "Move dispatcher to 08:30." · "Turn off deep daydream."

The system learns from your clicks. After three consistent uses of the same fix, the dashboard pre-selects it as a "✨ suggested" action — you accept or reject. Reversals trigger an automatic safety brake.

CLEAR — the methodology

Five principles, one rule each:

C — Contextual Ownership · one document owns each topic. No duplicates.
L — Linking · reference sources; don't copy them.
E — Elimination · consolidate; don't keep two versions.
A — Alignment · context that doesn't support decisions doesn't belong.
R — Refinement · structured maintenance, not ad-hoc fixes.

The whole framework is the mechanical implementation of these five rules.

What ships

Everything below installs as one repo drop-in. No third-party services, no logins, no telemetry — all state lives in your .claude/ and docs/ folders.

Layer	Count	Examples
Skills (chat-invokable via slash command)	17	`clear-planner` · `bcos-wiki` · `context-routing` · `context-audit` · `context-ingest` · `daydream` · `learning` · `schedule-tune` · `lessons-consolidate` · `ecosystem-manager`
Sub-agents (delegated bounded tasks)	3	`wiki-fetch` · `explore` · plus one optional
Scripts (mechanical Python)	46	`lifecycle_sweep` · `run_wiki_` (5) · `cmd_wiki_` (7) · `auto_fix_audit` · `bcos_inventory` · `digest_sidecar` · `record_resolution`
Hooks (auto-validation on edit)	4	post-edit frontmatter check · post-commit context check · pre-compact save · auto-save session
Maintenance jobs (scheduled, one dispatcher)	12	`index-health` · `audit-inbox` · `daydream-lessons` · `daydream-deep` · `architecture-review` · `auto-fix-audit` · `lifecycle-sweep` · `wiki-stale-propagation` · `wiki-source-refresh` · `wiki-graveyard` · `wiki-coverage-audit` · `wiki-canonical-drift`
Auto-fix IDs (silent dispatcher fixes)	12	`missing-last-updated` · `eof-newline` · `frontmatter-field-order` · `wiki-mark-queue-ingested` · `wiki-archive-expired-post-mortem`
Architecture docs	12	`wiki-zone.md` · `lifecycle-routing.md` · `typed-events.md` · `context-zones.md` · `content-routing.md` · `wiki-headless-scripts.md`
Methodology docs	5	CLEAR principles · context architecture · decision framework · document standards · ownership specification
Project patterns (starting templates by project type)	8	client-project · gtm · marketing · operational · product-development · product-service · internal-tool-app · internal-tool-automation
Templates (frontmatter, schema, starters)	15	data-point · cluster · current-state · table-of-context · wiki-schema · wiki-config · session-diary-starter

Every script and skill is documented at the source. Every job has a reference doc under .claude/skills/schedule-dispatcher/references/job-*.md. Every typed-event finding maps to a renderer in the dashboard cockpit. Adding a new check means dropping a cmd_*.py or run_*.py, registering it in one map, and the dashboard picks it up.

Contributing

Contributions welcome — open an issue or submit a PR targeting the dev branch. CI runs frontmatter, reference, and ecosystem-integration checks on every PR.

The fastest contribution path is lessons learned. As you use the system it captures insights; if you find one universal, contribute it back.

Origin

Built by Guntis Coders after two years of operating context systems in production. The CLEAR methodology emerged from a practical problem: AI context degrades silently, and no amount of one-time documentation prevents it. The solution required a system — ownership boundaries, automated maintenance, self-learning, and structured reflection.

Background: What is the Table of Contexts and why does it matter.

License

MIT

docs/_bcos-framework/architecture/permissions-catalog.md

name: "Permissions Catalog" type: reference cluster: "BCOS Framework" version: "1.0.0" status: active created: "2026-05-07" last-updated: "2026-05-07"

Permissions Catalog

Ownership Specification

DOMAIN: Source of truth for the Claude Code permissions BCOS ships in .claude/settings.json. Maps every permissions.allow entry to the script, skill, file path, or workflow that depends on it.

EXCLUSIVELY_OWNS:

The canonical list of permissions BCOS expects to be present at install time
The mapping from each permission to the BCOS component(s) that need it
The rationale for why each permission is shipped vs. left for user approval at runtime

STRICTLY_AVOIDS:

The actual settings files themselves (this catalog documents what they should contain; the managed surfaces — .claude/settings.json and ~/.claude/settings.json — live where they live)
Hook configuration semantics (see docs/_bcos-framework/architecture/system-design.md)
Skill author conventions for declaring required permissions (see how-to-extend)

Why this exists

Scheduled dispatcher runs spawn fresh Claude Code sessions with no human at the keyboard. Every permission prompt in those sessions becomes a stuck task. The fix is to ship the full set of permissions BCOS needs by default, so the dispatcher never has to ask.

This catalog is the SoT against which .claude/settings.json is maintained. When a new dispatcher job, script, or skill is added, the maintainer should:

Add the permission to .claude/settings.json (the live shipped file)
Add an entry here mapping the permission to the component
Confirm update.py's merge_settings_json will propagate the new entry to existing installs (it does, additively, by default)
Keep rules narrow — use prefix globs (:*), not blanket Bash, Edit, or Write rules.

Hand-added rules are preserved across updates. BCOS tracks only its own shipped rules via the _bcosManagedPermissions marker key. Anything else in permissions.allow is treated as user-added and never touched. If you remove a BCOS-shipped rule from allow by hand, BCOS respects that removal — see reset_permissions_marker.py to undo if you change your mind.

Catalog

Read access

Permission	Why needed
`Read(**)`	All BCOS components read across the repo. Read-only is low-risk and avoiding piecemeal Read rules keeps the file legible.
`Glob`	Used by every job that walks `docs/`, `_wiki/`, `.claude/skills/`, etc.
`Grep`	Used by `context-search`, `analyze_crossrefs`, `validate_references`, audit jobs.

Python script invocations

A catch-all prefix lets the dispatcher run any framework script without per-script approval. The explicit list below the catch-all is for clarity and as a fallback if a future Claude Code release tightens prefix semantics.

Permission	Why needed
`Bash(python .claude/scripts/:*)`	Catch-all: every framework script lives under `.claude/scripts/`. The dispatcher and jobs invoke them directly via `python <path>`.
`Bash(python3 .claude/scripts/:*)`	Same, for `python3` alias on systems that expose only python3.

Explicit per-script entries (also shipped — redundant with the catch-all but defensive):

Script	Used by
`append_diary.py`	dispatcher Step 4 (every job appends a diary entry)
`build_document_index.py`	`index-health`, `audit-inbox`, `architecture-review`, `daydream-deep`, `wiki-coverage-audit`
`generate_wakeup_context.py`	`index-health` Step 2
`analyze_crossrefs.py`	`daydream-deep` Step 2
`analyze_integration.py`	`architecture-review` Step 3 (`--ci` mode)
`prune_sessions.py`	auto-fix `prune-sessions` (whitelisted)
`prune_diary.py`	auto-fix `prune-diary` (whitelisted)
`refresh_ecosystem_state.py`	`index-health` Step 3, `architecture-review` Step 3, auto-fix `ecosystem-state-refresh`
`refresh_wiki_index.py`	`index-health` Step 4, `wiki-coverage-audit`, `wiki-stale-propagation`, auto-fix `wiki-index-refresh`
`lifecycle_sweep.py`	`lifecycle-sweep` job (preferred headless path)
`auto_fix_audit.py`	`auto-fix-audit` job (resolution-log auditor)
`scan_docs_structure.py`	`index-health` Step 5 (replaces the prose scan/auto-fix loop; emits JSON with findings + applied fixes)
`context_index.py`	dispatcher Step 2.5 (regenerates `.claude/quality/context-index.json` once per run)
`context_search.py`, `context_bundle.py`	`context-routing` skill (`/context search`, `/context bundle`)
`promote_resolutions.py`	self-learning ladder (regenerates `learned-rules.json`)
`record_resolution.py`	resolution log writer for auto-fixes and headless clicks
`digest_sidecar.py`	dispatcher Step 7 (writes `daily-digest.json` for dashboard)
`consolidate_lessons.py`, `find_lessons.py`	`lessons-consolidate` skill
`bcos_inventory.py`	ecosystem state inventory
`load_zone_registry.py`, `load_task_profiles.py`, `validate_task_profiles.py`	shared loaders for context-routing, used by multiple skills
`validate_frontmatter.py`, `validate_references.py`	CI hooks and `index-health`
`validate_permissions_catalog.py`	CI hook `validate-permissions-catalog` (drift guard between this catalog and `.claude/settings.json`). Bidirectional check — flags catalog entries missing from settings AND settings entries with no catalog rationale row. Advisory (continue-on-error).
`audit_node_configs.py`	Portfolio-level cold-scan equivalent of the runtime Step 4a preflight in `schedule-dispatcher/SKILL.md`. Walks every BCOS-installed sibling under `--root`, scans each enabled job's `job-{name}.md` spec for cross-repo references (`../` segments + absolute paths outside the sandbox), returns `{scanned, clean, violations}` JSON. Read-only; exit code always 0 so it can wire as advisory CI. Pairs with the typed-event `node-job-cross-repo-reference` emitted at runtime.
`wiki_schema.py`	every wiki job (`wiki-source-refresh`, `wiki-graveyard`, `wiki-coverage-audit`) validates schema before scanning
`wiki_failed_ingest.py`	`wiki-failed-ingest` job
`run_wiki_canonical_drift.py`	`wiki-canonical-drift` job
`run_wiki_coverage_audit.py`	`wiki-coverage-audit` job
`run_wiki_graveyard.py`	`wiki-graveyard` job
`run_wiki_source_refresh.py`	`wiki-source-refresh` job
`run_wiki_stale_propagation.py`	`wiki-stale-propagation` job
`cmd_wiki_*.py`	individual `bcos-wiki` slash commands (`/wiki init`, `/wiki lint`, etc.)
`update.py --dry-run`, `update.py --check`	safe to allow; the destructive `update.py` (no flag) requires explicit user approval each time
`record_daydream.py`	`daydream` skill Step 6 (writes `.claude/quality/last-daydream.txt`). Replaces an earlier `echo > .claude/quality/last-daydream.txt` shell-redirect that doesn't fit the allowlist shape.
`ensure_wiki_zone.py`	`update.py` substrate guarantee — idempotent wiki-zone scaffold for users upgrading from pre-wiki installs. Invoked via `subprocess.run`, not a skill, so no Bash rule needed; listed here for completeness.

Bash utilities

Permission	Why needed
`Bash(bash .claude/scripts/set_profile.sh:*)`	Switch gitignore profile (shared/personal) — used during onboarding and update
`Bash(bash .claude/agents/agent-discovery/find_agents.sh)`, `Bash(bash .claude/agents/agent-discovery/find_agents.sh:*)`	Agent discovery — bare invocation AND with args per same skills as above.
`Bash(python .github/scripts/validate_frontmatter.py:)`, `Bash(python .github/scripts/validate_references.py:)`, `Bash(python3 .github/scripts/validate_frontmatter.py:)`, `Bash(python3 .github/scripts/validate_references.py:)`	`ecosystem-manager` Step 3 (CI validation) runs the GitHub Actions mirror copies of these validators locally so engineers see the same results CI will. Both `python` and `python3` invocation forms shipped for portability.
`Bash("$CLAUDE_PROJECT_DIR/.claude/bin/python3" .claude/scripts/:)`, `Bash("$CLAUDE_PROJECT_DIR/.claude/bin/python3" .claude/hooks/:)`	Quoted-shim Python invocation form used by `context-onboarding` and any skill that hits `_claude_md.py`. Required because Claude Code matches the literal command prefix character-by-character — quoted and unquoted shim paths are different rules.
`Bash(cat .claude/quality/last-daydream.txt)`, `Bash(cat .claude/quality/last-daydream.txt:*)`	`daydream` Step 1 reads the timestamp to compute the diff window. Read-only; narrow.
`Bash(mkdir -p .claude/hook_state:)`, `Bash(mkdir -p .claude/quality/sessions:)`, `Bash(mkdir -p .claude/quality/ecosystem:)`, `Bash(mkdir -p docs/_inbox:)`, `Bash(mkdir -p docs/_archive:)`, `Bash(mkdir -p docs/_planned:)`, `Bash(mkdir -p docs/_collections:)`, `Bash(mkdir -p docs/_wiki:)`	Directory creation for BCOS-managed paths, including dynamic subdirectories like clear-planner's session folders (`.claude/quality/sessions/{YYYYMMDD}_{HHMMSS}_{slug}/`). Each rule is scoped to a specific BCOS path; we deliberately do NOT ship blanket `Bash(mkdir:*)`.
`Bash(touch .claude/hook_state/.gitkeep)`	Maintain gitkeep markers
`Bash(chmod +x .claude/hooks/:)`, `Bash(chmod +x .claude/scripts/:)`	Make shell hooks executable on first install (Linux/macOS)

Skill author rule — use relative paths only. The mkdir rules above only match if the skill invokes mkdir with a relative path from the project root (e.g. mkdir -p .claude/quality/sessions/foo). If a skill expands the path to an absolute form (mkdir -p "$CLAUDE_PROJECT_DIR/.claude/quality/sessions/foo" or a hardcoded C:/Users/.../foo) the rule will not match and the unattended session will hit a permission prompt. Skills should always use the relative path verbatim — Claude Code is rooted at the project directory, so relative paths Just Work. This is documented in clear-planner's Step 1 as a blocking instruction.

Git operations

The dispatcher's auto-commit step (Step 7b) and the headless action handlers need a narrow set of git commands. We do NOT ship git push or any destructive operation.

Permission	Why needed
`Bash(git status)`, `Bash(git status --porcelain)`, `Bash(git status --porcelain:*)`	Auto-commit clean-tree check
`Bash(git rev-parse --abbrev-ref HEAD)`, `Bash(git rev-parse:*)`	Branch allowlist check, current-commit detection
`Bash(git diff --stat HEAD)`, `Bash(git diff --stat:)`, `Bash(git diff --name-only:)`	Pre-commit summary, ecosystem audit
`Bash(git log --oneline:)`, `Bash(git log -n:)`	Recent-history checks for daydream + diff resolution
`Bash(git branch --show-current)`	Branch detection (publish.sh, dispatcher)
`Bash(git remote -v)`	Remote checks during update.py
`Bash(git add docs/document-index.md)` etc. (specific files)	Auto-commit Step 7b — only files in the ALLOWED list are addable
`Bash(git commit -m bcos:*)`	Auto-commit Step 7b — message always begins `bcos: daily maintenance ...`

We deliberately do NOT ship: git push, git reset, git checkout, git mv, git rm, git revert. These need user confirmation each time. (The dispatcher never invokes them; headless actions that propose them are surfaced as one-click cards in the dashboard, not silent.)

Edit/Write — files BCOS owns

Path glob	Used by
`.claude/hook_state/**`	Diary file, hook state, session capture
`.claude/quality/ecosystem/**`	`state.json`, `lessons.json`, `resolutions.jsonl`, `learned-rules.json`, `learning-blocklist.json`
`.claude/quality/schedule-config.json`	`schedule-tune` skill writes here
`.claude/quality/context-index.json`	dispatcher Step 2.5 cache
`.claude/quality/bcos-inventory.json`	`bcos_inventory.py`
`.claude/quality/sessions/**`	session capture files
`.claude/quality/atlas-ignore.json`	atlas exclusion list
`docs/.wake-up-context.md`	`index-health` Step 2 (regenerated)
`docs/.session-diary.md`	hooks + `prune-diary` auto-fix
`docs/.onboarding-checklist.md`	`context-onboarding` skill
`docs/document-index.md`	`build_document_index.py` (regenerated)
`docs/_inbox/**`	`daily-digest.md`, `daily-digest.json`, captured material
`docs/_planned/**`	AI-generated plans synthesised from inbox material, transcripts, daydream output, etc. — usually framework-authored, not hand-typed
`docs/_archive/**`	archive-on-supersede moves
`docs/_wiki/index.md`	`refresh_wiki_index.py` (regenerated)
`docs/_wiki/log.md`	wiki ingest log
`docs/_wiki/queue.md`	wiki queue (mark-ingested fix)
`docs/_wiki/overview.md`	wiki overview metadata
`docs/_wiki/.archive/**`	archived wiki pages
`docs/_wiki/raw/**`	wiki raw captures
`docs/_wiki/source-summary/**`	external-reference summaries
`docs/_wiki/pages/**`	authored wiki pages

We deliberately do NOT ship blanket Edit(docs/**) / Write(docs/**). Canonical data points (docs/*.md at the root) are user-authored — every edit there should ask, even from inside the dispatcher. docs/_collections/** (verbatim evidence — invoices, contracts, transcripts) and docs/_bcos-framework/** (framework files, only changed via update.py) are also off-limits to dispatcher writes.

Skills the dispatcher delegates to

Skill	Used by
`schedule-dispatcher`	the cron task itself
`schedule-tune`	dispatcher Step 8 (apply suggestions), user requests
`context-audit`	`audit-inbox`, `architecture-review`
`context-ingest`	`lifecycle-sweep` (route-to-collection delegates to Path 5)
`context-routing`	`/context search`, `/context bundle`
`daydream`	`daydream-lessons`, `daydream-deep`
`doc-lint`	quality gates
`ecosystem-manager`	meta-skill operations
`lessons-consolidate`	`audit-inbox` (report-only) and direct invocation
`bcos-wiki`	`wiki-source-refresh` (refresh path), `lifecycle-sweep` (promote-to-wiki), all `/wiki *` commands
`learning`	self-learning ladder management
`clear-planner`	planning gates for non-trivial changes
`context-onboarding`	first-run flow
`context-mine`	conversation export ingestion
`core-discipline`	always-active skill discovery enforcer

Permissions NOT shipped — left for user approval at runtime

These tools are deliberately omitted from the shipped allowlist because:

mcp__scheduled-tasks__* — depends on the user having the scheduled-tasks MCP server configured. Onboarding Step 6 explicitly tells the user to pick "Always allow" on the first prompt, which adds it to their personal allowlist.
WebFetch, WebSearch — used during ingest and capture, but the URLs vary per request. Approving wholesale would be too broad. The user is normally at the keyboard during ingest.
Bash(git push:*), Bash(git reset:*), Bash(git mv:*), Bash(git revert:*), Bash(rm:*) — destructive. The dispatcher never needs them. Headless action handlers that propose moves surface as one-click dashboard cards instead.
Generic Bash, Edit, Write — too broad. We allowlist specifically.

Managed permission surfaces

BCOS manages two distinct settings surfaces. Each has its own writer, its own contract for user-added content, and its own boundary.

Surface	Writer	Marker key	What gets written	What's never touched
`.claude/settings.json` (project-level)	`install.sh` + `update.py:merge_settings_json`	`_bcosManagedPermissions`	Every entry in the Catalog table above. Marker-aware reconciler: rules in `permissions.allow` not in the marker are treated as user-added and preserved. Tombstoned removals are respected.	User-added rules in `permissions.allow`, user's own `permissions.deny`, hook entries outside BCOS's hooks block, any top-level key BCOS doesn't own.
`~/.claude/settings.json` (user-level cross-repo mirror)	`install_global_permissions.py`	(none — additive merge against existing user content)	The same `permissions.allow` entries from the project allowlist. Hooks are NOT mirrored (project-specific by design). Re-running is a no-op.	Anything else in user-level settings. The script never deletes user rules — revocation is the user's call.

Surface 1: project-level `.claude/settings.json`

This catalog's main "Catalog" table above is the SoT. The shipped settings.json mirrors it 1:1 plus a small set of structural entries (Read(**), Glob, Grep) that don't need a catalog row. Drift between the two is caught by validate_permissions_catalog.py — run on every commit via CI and on every onboarding.

Marker-aware reconciler. update.py:merge_settings_json tracks BCOS's shipped rules in a top-level _bcosManagedPermissions key. The five reconciler states are:

ADD — rule is in shipped catalog, not yet in allow → append.
ADOPT — rule is in shipped catalog, already in allow (e.g. you manually added it before BCOS shipped it) → record in marker, leave allow alone.
NOOP — rule is in shipped catalog, in allow, in marker → steady state.
RESPECT_USER_REMOVAL (tombstone) — rule is in shipped catalog, in marker, removed from allow → leave removed forever. Run python .claude/scripts/reset_permissions_marker.py to undo.
REVOKE — rule no longer in shipped catalog but still in marker → drop from allow and marker.

User-added rules (in allow, not in marker, not in shipped catalog) are invisible to the reconciler. Touched by no codepath.

Surface 2: cross-repo mirror surface — `~/.claude/settings.json`

The project surface is project-local: it applies only when Claude is rooted in this repo. When BCOS schedules and workflows span multiple repos, every cross-repo write hits a permission prompt and the unattended scheduled session stalls.

The fix: mirror this allowlist into ~/.claude/settings.json (user-level, applies everywhere)

python .claude/scripts/install_global_permissions.py            # apply
python .claude/scripts/install_global_permissions.py --dry-run  # preview first

The merge is additive — your existing user-level rules are never removed, replaced, or reordered. Re-running the script is a no-op once everything is in sync.

What gets mirrored: every entry under permissions.allow from the project settings. Hooks are NOT mirrored (they're project-specific by design).

What this does to your trust model: a rule like Bash(python .claude/scripts/refresh_ecosystem_state.py:*) at user level allows that command in any repo on this machine that has a script of that name. If you only check out BCOS-installed repos (the script names are unambiguous and BCOS-owned), this is exactly what you want. If you frequently check out untrusted repos that might shadow BCOS script names, prefer the project-level approach and run BCOS install in each repo separately. Note: we don't ship blanket Bash/Edit/Write or destructive git commands at any level, so even at user-level the surface stays scoped.

To revoke later: open ~/.claude/settings.json and remove the rules you no longer want. The script never deletes anything from user-level settings.

Cross-workstation portability

The mirror script handles cross-repo coverage on one machine. Three things still don't travel between workstations on their own:

File / location	What it carries	Portability
`~/.claude/settings.json`	Cross-repo permissions written by `install_global_permissions.py`	Re-run the installer on each workstation, or bring your own `~/.claude/` sync mechanism
`~/.claude/scheduled-tasks/<task>.json`	Your actual cron/Task-Scheduler entries	Re-run onboarding Step 6 per machine, or bring your own `~/.claude/` sync mechanism
`~/.claude/projects/<project>/sessions/`	Conversation history	Stays per-machine — large, machine-specific, not useful to sync

Recommended setup for a multi-workstation maintainer: re-run install_global_permissions.py and onboarding Step 6 on each workstation. If you prefer to sync ~/.claude/ via an out-of-band file-sync tool, that works too — exclude ~/.claude/projects/*/sessions/ if you want conversation history machine-local.

For a single-workstation user: ignore the above; the mirror script is sufficient.

The same constraint applies to BCOS event-log files (.claude/quality/ecosystem/resolutions.jsonl etc.) which are deliberately gitignored on every profile — append-only logs across multi-machine workflows produce git merge conflicts that silently truncate the auditor's history. Git is not the mechanism for these files; an out-of-band file-sync tool is, if you need cross-machine continuity at all.

Testing / drift guards

Drift between any of the three managed surfaces and this catalog is caught by validate_permissions_catalog.py:

python .claude/scripts/validate_permissions_catalog.py

Bidirectional check:

Forward: every rule quoted in the "Catalog" table above must exist in .claude/settings.json > permissions.allow.
Reverse: every permissions.allow entry must have a catalog row OR be on the small structural-infra allowlist (Read(**), Glob, Grep).

Wired into CI (advisory; continue-on-error: true) as the validate-permissions-catalog job. Also invoked by context-onboarding Step 6b-pre — onboarding and CI consume the same drift check, so a fresh install can never start in a permission-drifted state.

Exit code 0 = clean. Exit code 1 = drift detected (with detailed report on stdout). Run it locally before opening a PR that touches settings.json or this catalog.

How to extend

Adding a new dispatcher job, script, or skill:

Determine the minimum set of new permissions needed (script invocation, write paths, sibling skill calls).
Edit .claude/settings.json and append to permissions.allow. Use a glob/prefix when reasonable, but stay narrow.
Add the corresponding rows to this catalog (under "Catalog" → matching subsection).
Run python .claude/scripts/update.py --dry-run against an existing install to confirm the additive merge picks up the new entries cleanly.
Document the new job/script in its reference file (.claude/skills/schedule-dispatcher/references/job-*.md) and link the permission rationale to this catalog if it's non-obvious.

Maintenance signals

Signal	What it means
Dispatcher runs report `verdict: error` with "permission denied" or "tool not allowed"	A new component slipped in without its permission. Find the offending tool call, add it here and to settings.json.
Existing install upgrades via `update.py` and the merge reports 0 new entries when this catalog has new rows	Either the rows were added but `.claude/settings.json` wasn't, or the rows were already present in the user's settings. Check both.
User reports "scheduled task didn't fire" or "stuck on permission prompt"	Open `~/.claude/projects/<project>/sessions/<latest>.jsonl` and grep for `permission` to see what was asked. Add it.

.claude/settings.json — the live shipped allowlist
.claude/scripts/update.py — the merge function (merge_settings_json)
.claude/scripts/_settings_reconciler.py — the marker-aware 5-state reconciler implementation
.claude/scripts/reset_permissions_marker.py — rescue command to drop the _bcosManagedPermissions marker (re-ADOPT current allow on next update)
.claude/scripts/install_global_permissions.py — Surface 2 (user-global mirror) writer
.claude/skills/context-onboarding/SKILL.md — Step 6b-pre verifies these entries are present
.claude/skills/schedule-dispatcher/references/auto-fix-whitelist.md — separate concern (which fixes are silent), parallel to this (which permissions are shipped)

278 files · 9 not served here

Advantages

Prevents context rot by surfacing stale information on a configurable schedule. evidence: README.md
Enforces ownership boundaries to ensure one source of truth per topic. evidence: README.md
Reduces token usage by providing a structured index that avoids redundant scanning. evidence: CLAUDE.md
Enables task-aware context retrieval through curated bundles. evidence: README.md

Limitations

Requires adherence to a specific folder structure and frontmatter schema to function correctly. evidence: README.md
Maintenance jobs and dispatcher functionality rely on Python and bash being available on the host system. evidence: README.md

Security

Risk level: Medium risk

This brain runs

Agent instructions that run or fetch something (170)

.claude/agents/wiki-fetch/AGENT.md: A 100k-token URL fetched into the main thread by `/wiki run` saturates the context window before a single page lands.
.claude/agents/wiki-fetch/AGENT.md: | Calling skill | Subcommand | Trigger | |---|---|---| | `bcos-wiki` | `run` Pass 1 | Each URL in the queue → one `wiki-fetch` invocation | | `bcos-wiki` | `refresh` full-tier | Source-summary past `stale_threshold_days` and HEAD signals changed | | `bcos-wiki` | `promote` (Path B) | S …[+132 chars] · uses the network
.claude/agents/wiki-fetch/AGENT.md: The cumulative budget guard ([`_wiki_budget.decide_dispatch_strategy`](../../scripts/_wiki_budget.py)) decides whether N sub-agents run in parallel or serial — `parallel` when projected cumulative tokens stay ≤ 80% of the main context limit;
.claude/agents/wiki-fetch/AGENT.md: queue an explicit retry tag for next run | | `error.kind: fetch-error` | 4xx/5xx from upstream | Surface to user;
.claude/agents/wiki-fetch/AGENT.md: `python .claude/scripts/test_wiki_fetch.py` — asserts this AGENT.md declares the documented input kinds and output fields, that the 4000-token cap is stated, that calling-skill docs reference both `wiki-fetch` and the Task tool, and that the result-schema validator + cumulative budget g …[+47 chars]
.claude/skills/bcos-wiki/SKILL.md: **`/wiki`** with subcommands: `init`, `init --defaults`, `run`, `queue`, `promote`, `create`, `review`, `archive`, `refresh`, `lint`, `remove`, `schema`, `search`
.claude/skills/bcos-wiki/SKILL.md: "Run the wiki refresh"
.claude/skills/bcos-wiki/SKILL.md: | | `run [<url>]` | implemented | P3 | Path A: batch (no arg) processes all `## Pending` queue items;
.claude/skills/bcos-wiki/SKILL.md: single (with URL) auto-queues + ingests | | `queue <url> [tags]` | implemented | P3 | Append URL to `## Pending` of `queue.md` without fetching | | `ingest` | shared protocol | P3 | Internal — called by `run`/`promote`/`create`;
.claude/skills/bcos-wiki/SKILL.md: optionally re-pull `builds-on` data points to verify | | `archive <slug>` | implemented | P3 | Soft-delete to `_wiki/.archive/` with dangling-reference scan | | `refresh <slug>` | implemented | P3 | Path A: re-fetch a `source-summary` page (refresh-must-rediscover applies, D-05 two-tie …[+470 chars]
.claude/skills/bcos-wiki/SKILL.md: `run` → `run.md`
.claude/skills/bcos-wiki/SKILL.md: Run `/wiki init` first."* and exit.
.claude/skills/bcos-wiki/SKILL.md: | Choice | Behavior | |---|---| | Init with defaults + proceed | Run `.claude/scripts/cmd_wiki_init.py` (or equivalent `ensure_wiki_zone.py` call).
.claude/skills/bcos-wiki/SKILL.md: Then resume the original subcommand (`create from`, `promote`, `run`, etc.) as if the Guard had passed.
.claude/skills/bcos-wiki/SKILL.md: | | Full interview + proceed | Read `init.md` and run the 6-question interactive scaffold.
.claude/skills/bcos-wiki/SKILL.md: The dispatched subcommand files (`create.md`, `promote.md`, `run.md`, `refresh.md`, `lint.md`, `archive.md`, `review.md`, `remove.md`, `schema.md`, `search.md`, `bundle.md`, `queue.md`) all reference *"the `.config.yml` Guard defined in `SKILL.md`"* — they inherit this AskUserQuestion p …[+46 chars]
.claude/skills/bcos-wiki/SKILL.md: The human reviews diffs and runs `git commit` / `git push` when ready. · uses the network
.claude/skills/bcos-wiki/SKILL.md: This applies to `run`, `refresh`, and `create` (when source content is large).
.claude/skills/bcos-wiki/SKILL.md: Users who want a binary in collections-as-evidence must run `/collections add` explicitly.
.claude/skills/bcos-wiki/SKILL.md: ├── run.md ← /wiki run [<url>]
.claude/skills/bcos-wiki/SKILL.md: ├── ingest.md ← shared ingest pipeline (called by run/promote/create/refresh)
.claude/skills/clear-planner/SKILL.md: Step 2: Run Discovery
.claude/skills/clear-planner/SKILL.md: { "step": 2, "name": "Run Discovery", "status": "in_progress" }
.claude/skills/clear-planner/SKILL.md: **Run all three discovery scripts:**
.claude/skills/clear-planner/SKILL.md: bash .claude/agents/agent-discovery/find_agents.sh
.claude/skills/clear-planner/SKILL.md: bash .claude/skills/skill-discovery/find_skills.sh
.claude/skills/clear-planner/SKILL.md: python .claude/scripts/find_lessons.py --tags "#{scenarioType}"
.claude/skills/clear-planner/SKILL.md: Run discovery scripts (Step 2 results)
.claude/skills/clear-planner/SKILL.md: | | ------------------- | ------------------------------------ | --------------------------------------------------------- | ------------------- | | Integration Audit | Detect stale references in ecosystem | `python .claude/scripts/analyze_integration.py --staged` + AI review | **YES …[+455 chars]
.claude/skills/clear-planner/SKILL.md: | Scenario | Key Requirement | | ----------------- | ------------------------------------------------------------------ | | **AGENTING** | Check for ecosystem overlaps + run integration audit before commit | | **DOCUMENTAT …[+76 chars]
.claude/skills/context-audit/SKILL.md: Run all five audit categories against the scoped files.
.claude/skills/context-audit/SKILL.md: python .claude/scripts/build_document_index.py
.claude/skills/context-ingest/SKILL.md: | Input shape | Dispatch to | Why | |-------------|-------------|-----| | HTTP/HTTPS URL (article, GitHub, YouTube) | `/wiki run <url>` (the `bcos-wiki` skill, Path A) | Wiki owns external-source ingest, banner citations, schema validation, refresh tier | | Path inside `docs/_inbox/` a …[+508 chars]
.claude/skills/context-ingest/SKILL.md: If the input is mixed (e.g. Slack export *and* a URL), do mine first, then handle the URL via `/wiki run` separately, then return to ingest for whatever's left.
.claude/skills/context-ingest/SKILL.md: Run `python .claude/scripts/build_document_index.py` after material changes
.claude/skills/context-ingest/SKILL.md: **→ Rebuild Document Index** — Always: `python .claude/scripts/build_document_index.py`
.claude/skills/context-ingest/SKILL.md: **→ context-audit** — If a new data point was created: "Want me to run a quick CLEAR audit on the new doc?"
.claude/skills/context-mine/SKILL.md: Recommend: "Run context-ingest to classify and route these items"
.claude/skills/context-onboarding/SKILL.md: | What you see | What you do | |---|---| | User shares a URL, pitch deck, or describes their business | Gather from those sources, ask 2-3 follow-ups if needed | | Repo already has docs/, README, markdown files with business content | Scan the repo, map what exists | | User drops files …[+394 chars] · uses the network
.claude/skills/context-onboarding/SKILL.md: Before anything else, run **once** per onboarding session to make sure the BCOS-managed instructions are present in `CLAUDE.md`.
.claude/skills/context-onboarding/SKILL.md: This catches the `git clone`-without-`install.sh` case: if `CLAUDE.md` exists but lacks the `` / `` markers, the framework section is missing or unstructured. · uses the network
.claude/skills/context-onboarding/SKILL.md: If `.claude/bcos-claude-reference.md` doesn't exist yet (fresh clone), point `--source` at the upstream template available in this repo's tree (the same file install.sh would have copied).
.claude/skills/context-onboarding/SKILL.md: **First-run routing principle:** onboarding is allowed to identify all BCOS zones, but it should only create active data points after the user approves the architecture.
.claude/skills/context-onboarding/SKILL.md: | Material | First-run handling | |---|---| | Canonical facts, current decisions, project/task/business reality | Draft active data points in `docs/*.md` | | Raw notes, unsorted snippets, uncertain material | Keep in `docs/_inbox/` until triaged | | Future ideas, plans, or maybes | Par …[+578 chars]
.claude/skills/context-onboarding/SKILL.md: Options: **Activate** (set all to active, run index + wake-up) / **Adjust** (tell me what to fix)
.claude/skills/context-onboarding/SKILL.md: Run `python .claude/scripts/build_document_index.py` to generate the Document Index with DOMAIN one-liners
.claude/skills/context-onboarding/SKILL.md: Run `python .claude/scripts/generate_wakeup_context.py` to generate the Wake-Up Context for instant session orientation
.claude/skills/context-onboarding/SKILL.md: The checklist ships with install at `docs/.onboarding-checklist.md`.
.claude/skills/context-onboarding/SKILL.md: Ensure the `.claude/hook_state/` directory exists (it usually does from install.sh — check and create if missing).
.claude/skills/context-onboarding/SKILL.md: the dispatcher will create it on first run.
.claude/skills/context-onboarding/SKILL.md: **Run the catalog drift guard:**
.claude/skills/context-onboarding/SKILL.md: python .claude/scripts/validate_permissions_catalog.py
.claude/skills/context-onboarding/SKILL.md: python .claude/scripts/update.py
.claude/skills/context-onboarding/SKILL.md: Re-run the validator to confirm clean.
.claude/skills/context-onboarding/SKILL.md: If the answer is "Yes, multi-repo" (or the user confirms after explanation), run:
.claude/skills/context-onboarding/SKILL.md: python .claude/scripts/install_global_permissions.py
.claude/skills/context-onboarding/SKILL.md: Question: "When should the morning dispatcher run?"
.claude/skills/context-onboarding/SKILL.md: Run the schedule-dispatcher skill to execute today's scheduled CLEAR maintenance. It will:
.claude/skills/context-onboarding/SKILL.md: 3. Execute each job in sequence, appending one diary entry per job
.claude/skills/context-onboarding/SKILL.md: The portfolio aggregator picks it up on the next dispatcher run.
.claude/skills/context-onboarding/SKILL.md: The dispatcher will run in the wrong directory and writes meant for this repo's `docs/_inbox/` will be blocked.
.claude/skills/context-onboarding/SKILL.md: If "Recreate", call `mcp__scheduled-tasks__delete_event` (or the equivalent delete tool) on the bad task, then re-run Step 6d.
.claude/skills/context-onboarding/SKILL.md: That's intentional — fresh setups should over-monitor for the first 1-2 weeks until the auto-tuner suggests reductions after green-run streaks.
.claude/skills/context-onboarding/SKILL.md: Let the user invoke the first run on their terms.
.claude/skills/context-onboarding/SKILL.md: A fresh install has nothing to migrate and should never see the word.
.claude/skills/core-discipline/SKILL.md: **Significant change** (restructure a cluster, create new skills) → use clear-planner, run the full workflow
.claude/skills/core-discipline/SKILL.md: | Task Type | Action | | ------------------------- | ---------------------- | | Questions, commands | Respond directly | | Single-file fixes | Just do it | | Small changes (1-3 files) | Think briefly, execute |
.claude/skills/core-discipline/SKILL.md: A scheduled dispatcher run finishes clean green with zero findings (one-line summary keeps the dashboard "Ready" status meaningful)
.claude/skills/core-discipline/SKILL.md: **Special case — wrapping scripts with built-in prompts** (like `update.py`'s `[y/N]` prompt): invoke the script with `--dry-run` first, parse the output, surface the summary via `AskUserQuestion`, then re-invoke with `--yes` based on the user's choice.
.claude/skills/daydream/SKILL.md: If the file doesn't exist, this is the first run — use 2 weeks ago as the baseline.
.claude/skills/daydream/SKILL.md: # Read last run timestamp (or default to 2 weeks ago)
.claude/skills/daydream/SKILL.md: cat .claude/quality/last-daydream.txt 2>/dev/null || echo "no previous run"
.claude/skills/daydream/SKILL.md: git log --since="{last_daydream_date}" --name-only --pretty=format:"%h %s (%ar)" -- docs/ ':!docs/_bcos-framework/methodology/' ':!docs/_bcos-framework/guides/' ':!docs/_bcos-framework/templates/'
.claude/skills/daydream/SKILL.md: Report "No document changes since last run" and skip to Phase 3 (Imagine) for forward-looking reflection only.
.claude/skills/daydream/SKILL.md: git diff {last_daydream_commit}..HEAD -- docs/path/to/changed-file.md
.claude/skills/daydream/SKILL.md: python .claude/scripts/build_document_index.py --dry-run
.claude/skills/daydream/SKILL.md: python .claude/scripts/generate_wakeup_context.py
.claude/skills/daydream/SKILL.md: **Step 5b: Run maintenance scripts**
.claude/skills/daydream/SKILL.md: Daydream is the natural time to run periodic maintenance:
.claude/skills/daydream/SKILL.md: python .claude/scripts/prune_sessions.py
.claude/skills/daydream/SKILL.md: python .claude/scripts/prune_diary.py
.claude/skills/daydream/SKILL.md: python .claude/scripts/generate_wakeup_context.py
.claude/skills/daydream/SKILL.md: python .claude/scripts/analyze_crossrefs.py
.claude/skills/daydream/SKILL.md: **Step 6: Record this run**
.claude/skills/daydream/SKILL.md: python .claude/scripts/record_daydream.py
.claude/skills/daydream/SKILL.md: **Document Index** — Run `python .claude/scripts/build_document_index.py` if files changed
.claude/skills/doc-lint/SKILL.md: If `.md`: Run markdown quality checks and cross-reference validation
.claude/skills/doc-lint/SKILL.md: If `.json`: Run JSON structure validation
.claude/skills/doc-lint/SKILL.md: Px_001: Run markdown quality check -> doc-lint (markdown category)
.claude/skills/doc-lint/SKILL.md: Px_002: Run example code validation -> doc-lint (cross_reference category)
.claude/skills/doc-lint/SKILL.md: Px_001: Run JSON structure validation -> doc-lint (json_structure category)
.claude/skills/doc-lint/SKILL.md: Px_002: Run markdown quality check -> doc-lint (markdown category)
.claude/skills/ecosystem-manager/SKILL.md: Run discovery to see what exists:
.claude/skills/ecosystem-manager/SKILL.md: bash .claude/agents/agent-discovery/find_agents.sh
.claude/skills/ecosystem-manager/SKILL.md: bash .claude/skills/skill-discovery/find_skills.sh
.claude/skills/ecosystem-manager/SKILL.md: Run it before committing.
.claude/skills/ecosystem-manager/SKILL.md: python .claude/scripts/analyze_integration.py --uncommitted
.claude/skills/ecosystem-manager/SKILL.md: Coverage gaps in install.sh, settings.json, state.json, .gitignore
.claude/skills/ecosystem-manager/SKILL.md: Add fix tasks to the plan and execute them before committing.
.claude/skills/ecosystem-manager/SKILL.md: [ ] **install.sh installs new files**
.claude/skills/ecosystem-manager/SKILL.md: Run after major development sessions or as part of monthly architecture review.
.claude/skills/ecosystem-manager/SKILL.md: Run `python .claude/scripts/wiki_schema.py list` to inspect page-types, lint-checks, and auto-fixes from `_wiki/.schema.yml` or the framework fallback.
.claude/skills/ecosystem-manager/SKILL.md: Run all 4 CI checks locally:
.claude/skills/ecosystem-manager/SKILL.md: python .github/scripts/validate_frontmatter.py # YAML metadata on all managed markdown
.claude/skills/ecosystem-manager/SKILL.md: python .github/scripts/validate_references.py # All registry paths resolve + state.json accuracy
.claude/skills/ecosystem-manager/SKILL.md: python .claude/scripts/analyze_integration.py --ci # Ecosystem wiring (install.sh, settings.json coverage)
.claude/skills/learning/SKILL.md: **Mechanism:** `python .claude/scripts/promote_resolutions.py` (the module's `__main__` calls `regenerate()`).
.claude/skills/learning/SKILL.md: Run the matching subcommand directly.
.claude/skills/lessons-consolidate/SKILL.md: python .claude/scripts/consolidate_lessons.py
.claude/skills/schedule-dispatcher/SKILL.md: Run `python .claude/scripts/update.py` first."
.claude/skills/schedule-dispatcher/SKILL.md: Report to the user: "schedule-config.json is malformed — fix before the dispatcher can run.
.claude/skills/schedule-dispatcher/SKILL.md: For each entry in `jobs`, decide if it should run today.
.claude/skills/schedule-dispatcher/SKILL.md: | `schedule` value | Runs when | |--------------------|----------------------------------------------------| | `"daily"` | Every day | | `"mon"`..`"sun"` | Only on that weekday …[+549 chars]
.claude/skills/schedule-dispatcher/SKILL.md: **For on-demand dispatch** (user said "run the audit-inbox job"): skip this step, run only the named job.
.claude/skills/schedule-dispatcher/SKILL.md: Build an ordered list of jobs to run.
.claude/skills/schedule-dispatcher/SKILL.md: python .claude/scripts/context_index.py --write
.claude/skills/schedule-dispatcher/SKILL.md: The cache TTL is 10 min (longer than a full dispatcher cycle), so all jobs in this run hit the same in-memory snapshot.
.claude/skills/schedule-dispatcher/SKILL.md: Last run timestamp per job?
.claude/skills/schedule-dispatcher/SKILL.md: Use the helper script — it creates `.claude/hook_state/` on first run and matches the allowlisted command prefix so it never prompts:
.claude/skills/schedule-dispatcher/SKILL.md: python .claude/scripts/append_diary.py '{"ts":"2026-04-15T09:04:12","job":"index-health","verdict":"green","findings_count":0,"auto_fixed":[],"actions_needed":[],"duration_s":4}'
.claude/skills/schedule-dispatcher/SKILL.md: **Fallback:** when `.bcos-umbrella.json` is absent (standalone BCOS install with no umbrella), preflight reduces to the `../` + absolute-path scans — no sibling-name list to check against.
.claude/skills/schedule-dispatcher/SKILL.md: After Step 4 completes (last job returned), verify that **every job listed in Step 2's run-list produced exactly one diary entry in this dispatcher tick**.
.claude/skills/schedule-dispatcher/SKILL.md: Read back the diary entries appended during this tick (use the dispatcher's in-memory record, or the tail of `.claude/hook_state/schedule-diary.jsonl` filtered to the current run's `ts` prefix if you're running on-demand).
.claude/skills/schedule-dispatcher/SKILL.md: **Added in schema 1.1.0.** Before applying auto-fixes (Step 5) or rendering the digest (Step 7), enrich each finding emitted in Step 4 with three computed fields and produce the run's headline string.
.claude/skills/schedule-dispatcher/SKILL.md: **Match against prior tick.** Scan diary entries from the **immediately-prior dispatcher tick** (the most-recent run before today, identified by the latest `ts` < today's run window).
.claude/skills/schedule-dispatcher/SKILL.md: | Run shape | Headline template | |---|---| | Green clean (0 findings, 0 framework) | "{Nth consecutive green run.}{recovery callout if any job verdict flipped error→green this tick.}" | | Green with frequency suggestions only | "All {N} jobs green.
.claude/skills/schedule-dispatcher/SKILL.md: And the run has a `headline` string ready for Step 7.
.claude/skills/schedule-dispatcher/SKILL.md: For each job run today, check recent diary:
.claude/skills/schedule-dispatcher/SKILL.md: **Last run was `error`** → suggest investigating, not frequency change
.claude/skills/schedule-dispatcher/SKILL.md: Both are overwritten each run.
.claude/skills/schedule-dispatcher/SKILL.md: Conditional sections render ONLY when their counts are non-zero — a green clean run is ~5 lines, an amber run with 5 findings is ~40 lines.
.claude/skills/schedule-dispatcher/SKILL.md: | 1 | `{emitted_by}` | `{primary_attr}` | {one-line meaning} | {`🔁 Nth run` if consecutive_runs ≥ 3, else blank} |
.claude/skills/schedule-dispatcher/SKILL.md: Run at {ISO timestamp} · `.claude/hook_state/schedule-diary.jsonl`
.claude/skills/schedule-dispatcher/SKILL.md: verdict emoji + finding count + inline status markers in Note column | | `💡 Suggestions` | `≥1` `frequency-suggestion` finding | Bullet list | | Footer | Always | Run timestamp, diary path, auto-commit status |
.claude/skills/schedule-dispatcher/SKILL.md: | Scenario | Verdict bar example | Top line | Action hint | |---|---|---|---| | Green clean | `**🟢 BCOS green** · 1 ran · 0 findings · 0 fixed · 4s` | `Headline string from Step 4c, e.g. "10th consecutive green run."` | `→ Nothing to act on.
.claude/skills/schedule-dispatcher/SKILL.md: Run `git rev-parse --abbrev-ref HEAD` to get the current branch.
.claude/skills/schedule-dispatcher/SKILL.md: This is the per-tick safety property: a stray hand-edit to a "generated" file on a day its owning job did not run still blocks auto-commit.
.claude/skills/schedule-dispatcher/SKILL.md: Globs are resolved against `git status --porcelain` paths (same surface the clean-tree rule already inspects).
.claude/skills/schedule-dispatcher/SKILL.md: **Emit the `job-missing-outputs-declaration` framework-finding only when** the job's run would have changed at least one path *outside* `GLOBAL_ALLOWED` (i.e. a path that *could* have been auto-committable had it been declared).
.claude/skills/schedule-dispatcher/SKILL.md: Run `git status --porcelain`.
.claude/skills/schedule-dispatcher/SKILL.md: `git commit -m "bcos: daily maintenance {YYYY-MM-DD}"` — no push, ever.
.claude/skills/schedule-dispatcher/SKILL.md: A BCOS install with no umbrella still writes the log — it just sits locally until somebody (or the dashboard) reads it.
.claude/skills/schedule-dispatcher/SKILL.md: The last thing the dispatcher does depends on whether the run produced anything that needs user judgement.
.claude/skills/schedule-dispatcher/SKILL.md: Otherwise — clean green run, zero findings, zero suggestions — output a short summary and stop.
.claude/skills/schedule-dispatcher/SKILL.md: **Why this rule:** if every run always asked a question, every scheduled run would show as "Awaiting input" in the dashboard even on clean days.
.claude/skills/schedule-dispatcher/SKILL.md: Or even shorter when the user is watching an on-demand run:
.claude/skills/schedule-dispatcher/SKILL.md: ("Do you want architecture review to run weekly?" is too abstract — `schedule-tune` handles that)
.claude/skills/schedule-dispatcher/SKILL.md: **Retry the failed job(s)** → re-run only the errored jobs (on-demand mode), then ask again with the new result
.claude/skills/schedule-dispatcher/SKILL.md: If the user says "run the {job-name} job now" or "run today's maintenance now":
.claude/skills/schedule-dispatcher/SKILL.md: Skip the schedule predicate — run only the named job(s)
.claude/skills/schedule-dispatcher/SKILL.md: ## On-demand run — {HH:MM} ({job-name})
.claude/skills/schedule-dispatcher/SKILL.md: If `daily-digest.md` does not yet exist (no scheduled run happened today), create it with a minimal header before appending the on-demand section.
.claude/skills/schedule-dispatcher/SKILL.md: DO append a diary entry per job with `"trigger":"on-demand"` so the run is tracked in history
.claude/skills/schedule-dispatcher/SKILL.md: Run another job
.claude/skills/schedule-dispatcher/SKILL.md: The morning scheduled run always OVERWRITES `daily-digest.md` fresh — so yesterday's on-demand sections are not preserved in the digest (diary retains them).
.claude/skills/schedule-dispatcher/SKILL.md: Every dispatcher run produces either a digest OR a user-facing error message.
.claude/skills/schedule-dispatcher/SKILL.md: `schedule-tune` — user-facing skill for changing config ("run audit twice a week")
.claude/skills/schedule-dispatcher/SKILL.md: If a run was wrong, add a corrective entry, don't mutate history.
.claude/skills/schedule-tune/SKILL.md: If you haven't set up BCOS scheduling yet, run `context-onboarding` Step 6.
.claude/skills/schedule-tune/SKILL.md: **Utterances:** *"run audit twice a week"*, *"change daydream to every 3 days"*, *"switch architecture review to quarterly"*, *"run index-health on weekdays only"*, *"audit on Tuesdays and Fridays"*
.claude/skills/schedule-tune/SKILL.md: **Utterances:** *"run the dispatcher at 08:30"*, *"move morning maintenance to 07:00"*
.claude/skills/schedule-tune/SKILL.md: Update the actual scheduled task's cron via `mcp__scheduled-tasks__update_scheduled_task` — that's what actually moves the run
.claude/skills/schedule-tune/SKILL.md: **Utterances:** *"what's my maintenance schedule?"*, *"when does audit run?"*, *"is architecture-review enabled?"*
.claude/skills/schedule-tune/SKILL.md: If the user proposes a cron that would run more than once per day, refuse: *"Dispatcher is designed to run once daily.
.claude/skills/schedule-tune/SKILL.md: | User says | Config edit | |----------------------------------------|----------------------------------------------------------------| | "run audit on Tuesday instead of Friday" | `jobs.audit-inbox.schedu …[+1012 chars]
.claude/skills/todo-utilities/SKILL.md: **Sequential Agent Invocation** — Tasks run one after another
CLAUDE.md: **Small changes (1-3 files)** — think briefly, execute.
CLAUDE.md: Auto-generated by `python .claude/scripts/generate_wakeup_context.py`.
CLAUDE.md: When unsure, run `context-ingest` and let it propose the route.
CLAUDE.md: **Post-work handoffs:** After integrating new content, offer to (a) rebuild the document index, (b) update related data points, (c) run an audit if architecture shifted.

Hooks (5)

.claude/settings.json (Stop): bash "$CLAUDE_PROJECT_DIR/.claude/hooks/auto_save_session.sh"
.claude/settings.json (PreCompact): bash "$CLAUDE_PROJECT_DIR/.claude/hooks/precompact_save.sh"
.claude/settings.json (PostToolUse): "$CLAUDE_PROJECT_DIR/.claude/bin/python3" "$CLAUDE_PROJECT_DIR/.claude/hooks/post_edit_frontmatter_check.py"
.claude/settings.json (PostToolUse): "$CLAUDE_PROJECT_DIR/.claude/bin/python3" "$CLAUDE_PROJECT_DIR/.claude/hooks/post_edit_frontmatter_check.py"
.claude/settings.json (PostToolUse): "$CLAUDE_PROJECT_DIR/.claude/bin/python3" "$CLAUDE_PROJECT_DIR/.claude/hooks/post_commit_context_check.py"

Install scripts (1)

install.sh: sh install.sh

Medium risk: runs-instruction-instruction-network (.claude/agents/wiki-fetch/AGENT.md:93)
Medium risk: runs-instruction-instruction-network (.claude/skills/bcos-wiki/SKILL.md:150)
Medium risk: runs-instruction-instruction-network (.claude/skills/context-onboarding/SKILL.md:33)
Medium risk: runs-instruction-instruction-network (.claude/skills/context-onboarding/SKILL.md:50)
Low risk: scripts-present (.claude/agents/agent-discovery/find_agents.sh)
Low risk: scripts-present (.claude/bin/python3)
Low risk: scripts-present (.claude/hooks/auto_save_session.sh)
Low risk: scripts-present (.claude/hooks/post_commit_context_check.py)
Low risk: scripts-present (.claude/hooks/post_edit_frontmatter_check.py)
Low risk: scripts-present (.claude/hooks/precompact_save.sh)
Low risk: scripts-present (.claude/scripts/analyze_crossrefs.py)
Low risk: scripts-present (.claude/scripts/analyze_integration.py)
Low risk: scripts-present (.claude/scripts/append_diary.py)
Low risk: scripts-present (.claude/scripts/audit_node_configs.py)
Low risk: scripts-present (.claude/scripts/auto_fix_audit.py)
Low risk: scripts-present (.claude/scripts/bcos_inventory.py)
Low risk: scripts-present (.claude/scripts/build_document_index.py)
Low risk: scripts-present (.claude/scripts/cmd_wiki_archive.py)
Low risk: scripts-present (.claude/scripts/cmd_wiki_init.py)
Low risk: scripts-present (.claude/scripts/cmd_wiki_lint.py)
Low risk: scripts-present (.claude/scripts/cmd_wiki_queue_add.py)
Low risk: scripts-present (.claude/scripts/cmd_wiki_remove.py)
Low risk: scripts-present (.claude/scripts/cmd_wiki_review.py)
Low risk: scripts-present (.claude/scripts/cmd_wiki_search.py)
Low risk: scripts-present (.claude/scripts/consolidate_lessons.py)
Low risk: scripts-present (.claude/scripts/context_bundle.py)
Low risk: scripts-present (.claude/scripts/context_index.py)
Low risk: scripts-present (.claude/scripts/context_search.py)
Low risk: scripts-present (.claude/scripts/digest_sidecar.py)
Low risk: scripts-present (.claude/scripts/find_lessons.py)
Low risk: scripts-present (.claude/scripts/generate_wakeup_context.py)
Low risk: scripts-present (.claude/scripts/install_global_permissions.py)
Low risk: scripts-present (.claude/scripts/lifecycle_sweep.py)
Low risk: scripts-present (.claude/scripts/load_task_profiles.py)
Low risk: scripts-present (.claude/scripts/load_zone_registry.py)
Low risk: scripts-present (.claude/scripts/promote_resolutions.py)
Low risk: scripts-present (.claude/scripts/prune_diary.py)
Low risk: scripts-present (.claude/scripts/prune_sessions.py)
Low risk: scripts-present (.claude/scripts/record_daydream.py)
Low risk: scripts-present (.claude/scripts/record_resolution.py)
Low risk: scripts-present (.claude/scripts/refresh_ecosystem_state.py)
Low risk: scripts-present (.claude/scripts/refresh_wiki_index.py)
Low risk: scripts-present (.claude/scripts/run_wiki_canonical_drift.py)
Low risk: scripts-present (.claude/scripts/run_wiki_coverage_audit.py)
Low risk: scripts-present (.claude/scripts/run_wiki_graveyard.py)
Low risk: scripts-present (.claude/scripts/run_wiki_source_refresh.py)
Low risk: scripts-present (.claude/scripts/run_wiki_stale_propagation.py)
Low risk: scripts-present (.claude/scripts/scan_docs_structure.py)
Low risk: scripts-present (.claude/scripts/set_profile.sh)
Low risk: scripts-present (.claude/scripts/update.py)

Attribution and licence

First committed by

walm00

Publisher

Guntis Coders (Community)

Source

walm00/business-context-os · commit 4635683

Licence

MIT License (files served here)

ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-12

Contributors

walm00

AutoGineer is not affiliated with or endorsed by walm00.

Install from source

9 of its files are not served here, so there is no ZIP. walm00/business-context-os at 4635683

What it is

How it works

Requirements

Set it up

Usage

Documentation by walm00

Install

From zero to running

What it does

The wiki zone

The dashboard

Requirements

Updating

Maintenance

CLEAR — the methodology

What ships

Contributing

Origin

License

name: "Permissions Catalog" type: reference cluster: "BCOS Framework" version: "1.0.0" status: active created: "2026-05-07" last-updated: "2026-05-07"

Permissions Catalog

Ownership Specification

Why this exists

Catalog

Read access

Python script invocations

Bash utilities

Git operations

Edit/Write — files BCOS owns

Skills the dispatcher delegates to

Permissions NOT shipped — left for user approval at runtime

Managed permission surfaces

Surface 1: project-level .claude/settings.json

Surface 2: cross-repo mirror surface — ~/.claude/settings.json

Cross-workstation portability

Testing / drift guards

How to extend

Maintenance signals

Related

Advantages

Limitations

Security

This brain runs

Attribution and licence

Install from source

Surface 1: project-level `.claude/settings.json`

Surface 2: cross-repo mirror surface — `~/.claude/settings.json`