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

.claude/skills/context-ingest/SKILL.md

name: context-ingest description: | The single entry point for getting anything new into your context architecture. Takes any input (documents, URLs, YouTube, meeting notes, pasted content) and triages it: dump to _inbox, park in _planned, or integrate into active docs.

WHEN TO USE:

"Here's a document — integrate it into my context"
"Save this for later" / "Dump these meeting notes"
"I have an idea — park it somewhere"
"Read this article — not sure if it's relevant"
"Our competitor just announced X — update positioning"
Any time new information needs to enter the context architecture
Raw material should become a wiki explainer rather than a canonical data point

Context Ingest

Purpose

This skill IS:

The entry point for getting new knowledge INTO your context architecture
A router that sends information to the correct owning data point
A classifier that determines what type of knowledge you're adding
The mechanism that makes your context system compound over time

This skill IS NOT:

Creating the initial context architecture (use context-onboarding for that)
Auditing existing context (use context-audit for that)
A raw file storage system (it extracts and integrates, not archives)

When to Use

"Here's our new brand guidelines PDF — integrate it" → integrate into active docs
"Save these meeting notes for later" → dump to _inbox/
"I have an idea about enterprise pricing" → park in _planned/
"I read this article — not sure if it's relevant" → triage — Claude reads, recommends a path
"Our competitor just launched a new product" → integrate into competitive positioning
"Watch this YouTube video and capture what matters" → triage — Claude extracts, asks where
"I pasted some notes — figure out where they belong" → triage — Claude classifies, user decides
"Fetch our brand doc from Google Drive" → fetch + integrate via MCP connector
"We have hundreds of call recordings in Notion" → map as external reference, don't copy

Front-door dispatch (use first)

context-ingest is the single public entry point for new material. Detect the input shape before asking the user, and dispatch to the specialist skill when one fits — don't make the user know which slash command to type.

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/` and user says "make this a wiki page"	`/wiki promote <path>` (Path B)	Wiki owns the `_inbox/` → `_wiki/pages/` promotion
Local file or pasted text — runbook, SOP, decision narrative, post-mortem, glossary entry, FAQ, transcript, research clipping, customer-call notes	`/wiki create from <path-or-paste>` (Path B)	Per plugin-storage-contract.md Rule 2, the wiki is the universal long-form / cross-cutting content destination. Don't route to `_collections/` (legal-weight only) or `docs/operations/<custom>` (that's a folder pattern that bypasses wiki tooling).
Slack export, meeting transcript, chat log, call recording transcript	`context-mine` first → its output lands in `_inbox/` → resume `context-ingest` triage on the result	Mine is the extraction preprocessor; ingest is the classifier/router. The processed `_inbox/` capture then typically routes to `/wiki promote` (transcripts are informational long-form content — Rule 2).
Loose notes, pasted text, brain dump, "save this for later"	Stay in `context-ingest` (use AskUserQuestion below)	This skill owns inbox/planned/active classification

If the dispatch is unambiguous (a URL is a URL), invoke the specialist directly and tell the user one sentence about what you did. 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.

Wiki zone not initialized? If the user's content routes to /wiki create from or /wiki promote but the target repo has no _wiki/ zone, the bcos-wiki SKILL.md Guard fires AskUserQuestion offering: (a) init with defaults + proceed [Recommended], (b) full interview + proceed, (c) cancel. Do not route around the wiki to docs/operations/<custom> or _collections/ — that creates a parallel storage path that breaks Rule 2's substrate guarantee.

context-routing (/context) is retrieval, not ingest — never dispatch there from here.

The Ingest Process

Step 1: Receive and Triage

Accept input in any form:

A file path (markdown, PDF, text)
A URL (Claude reads the page, YouTube videos, articles)
Pasted text in the conversation
A description of what changed ("we decided to pivot to enterprise")

Note what the source is and where it came from. This becomes the source citation.

Special case — session captures (docs/_inbox/sessions/*.md): These are auto-generated by the session save hooks. They already have frontmatter (type: session-capture) and are pre-structured into Decisions, Discoveries, Follow-ups, and Files Changed. When processing these:

Skip the triage question — they're already classified
Extract actionable items and route to owning data points
Check .claude/registries/entities.json for entity disambiguation
Delete the session file after successful integration (or leave it for prune_sessions.py)

For all other inputs, use the AskUserQuestion tool:

Question: "What do you want to do with this?"
Options: Save for later (dump to _inbox/) / It's an idea (park in _planned/) / Integrate it (classify and route to active docs) / Add to collection (bulk similar files) / Not sure (I'll read it and recommend)

User says...	Action	Where it goes
"Just save this for later" / "Dump it" / "I'll deal with it later"	Save as-is to `docs/_inbox/` with a descriptive filename. No processing needed. Done.	`docs/_inbox/meeting-2026-04-06.md`
"This is an idea" / "Might do this someday" / "Park it"	Extract the core concept, create a clean doc in `docs/_planned/`. Frontmatter recommended but linking optional. Done.	`docs/_planned/enterprise-tier.md`
"Integrate this" / "Update our context" / "This is real now"	Proceed to Step 2 below — full classify → find owner → integrate flow.	Active data points in `docs/`
"I have a bunch of these" / bulk similar files (call transcripts, reports, invoices)	Route to a collection folder. Keep original filenames. Append entry to collection index if one exists. See `docs/_bcos-framework/architecture/content-routing.md` Path 5.	`docs/_collections/[type]/`
"Make this a wiki page" / "Turn this into an explainer" / "_inbox item should become wiki"	Use the wiki-promotion path. Route existing `_inbox/` material to `/wiki promote`; route direct uploads, URLs, or pasted content to `/wiki create`.	`docs/_wiki/pages/` or `docs/_wiki/source-summary/`
"Not sure where this goes"	Read the content, show the user a summary + your recommendation (inbox / planned / integrate / collection), let them decide.	Depends on user choice

NEVER create folders not defined in the architecture. Valid destinations: docs/ (active), _inbox/, _planned/, _archive/, _collections/[type]/, and _wiki/ through the bcos-wiki skill. If content doesn't fit, ask the user.

For _inbox deposits: Create the file with a simple header:

# [Descriptive title]

**Source:** [URL / meeting / person]
**Date:** [today]
**Deposited by:** context-ingest (unprocessed)

---

[Raw content here]

For _planned deposits: Use the data point template but with relaxed requirements:

---
name: "[Concept Name]"
type: context
cluster: "[Best guess]"
status: draft
created: "[today]"
last-updated: "[today]"
# Optional: declare an exit trigger if the idea has a natural staleness clock
# lifecycle:
#   expires_after: 90d   # if untouched for 90d, lifecycle-sweep flags as idea-dead
---

## Concept

[Polished description of the idea]

## Why This Matters

[Why it might be worth doing]

## Open Questions

- [What needs to be figured out before this becomes active]

Step 1.5: Time-Bounded Content — Declare a Lifecycle Trigger

Whenever the captured content has a natural exit point — a proposal that will be sent, a meeting note that will fold into an SOP, a research dump that will become a wiki page, a dated snapshot that will be replaced — prompt the user to declare a lifecycle: frontmatter field. This is what makes the content self-describing for the lifecycle-sweep job (see docs/_bcos-framework/methodology/document-standards.md §"Lifecycle Triggers").

When to prompt (the captured content matches one of these shapes):

Content shape	Suggested lifecycle
Outbound draft (proposal, pitch, post, application)	`archive_when: "proposal-sent"` + `expires_after: 60d`
Meeting / call notes	`fold_into: <target-sop-or-engagement-doc>` + `expires_after: 14d`
Research dump with external URL(s)	`route_to_wiki_after_days: 30`
Dated analysis / point-in-time snapshot	`archive_when: "decision-made"` + `expires_after: 90d`
Call transcript or evidence file	`route_to_collection: "<type>"` + `archive_when: "outcome-known"`

How to prompt — use the AskUserQuestion tool:

Question: "This looks time-bounded. Declare a lifecycle exit trigger?"
Options: Yes — pick the suggested shape / Yes — let me specify / No — leave it open / Not sure — explain

If the user declines, the doc still works — the sweep will fall back to routing-rule pattern match. Adding a trigger upgrades it from "guessed" to "self-describing".

Step 2: Classify the Content

Only reach this step if the user chose "integrate" in Step 1.

Identify what KIND of knowledge this is AND how to handle it:

Content Type	Route To	Handling Mode
Company identity, mission, values	Company/identity data points	synthesize
Customer info, audience, segments	Audience data points	synthesize
Product/service changes	Product/value data points	synthesize
Process changes, workflow updates, SOPs	Process documents	wrap (preserve content)
Market shifts, competitor moves	Market/competitive data points	synthesize
Policy changes, rules, brand guidelines	Policy documents	wrap (preserve rules)
New facts, reference data, glossaries	Reference documents	catalog (preserve as-is)
Strategic decisions, direction changes	Strategy data points	synthesize
External bulk collections (100+ similar files)	External reference data point	map (don't copy)

Handling modes:

synthesize — combine from multiple sources into a new or updated data point
wrap — add CLEAR structure around existing content without changing it. Never rewrite SOPs, processes, or policies — a changed step could break a real workflow
catalog — add minimal frontmatter, keep content completely as-is
map — create a reference data point describing where to find external content

If the content spans multiple types, split it and route each piece separately.

Wiki-Promotion Path

Use this path when the content should become explanatory/wiki material, not a canonical active data point. The wiki owns derivative explainers, source summaries, glossaries, how-tos, and operational narratives that build on active docs without replacing them.

flowchart TD
    A["Incoming material"] --> B{"Wiki explainer or source summary?"}
    B -->|No| C["Continue normal context-ingest triage"]
    B -->|Yes, existing _inbox file| D["/wiki promote <path>"]
    B -->|Yes, direct file/paste/URL| E["/wiki create <source>"]
    D --> F["bcos-wiki shared ingest pipeline"]
    E --> F
    F --> G["docs/_wiki/pages or docs/_wiki/source-summary"]

Routing rules:

Existing material under docs/_inbox/ -> /wiki promote <path>.
Direct local file, paste, or URL -> /wiki create <source>.
URL queues that should be fetched later -> /wiki queue add <url>.
Canonical business facts still go to active data points first; wiki pages use builds-on to cite them.
Path B binaries stay inside docs/_wiki/raw/local/; do not write wiki-promoted files to _collections/ unless the user explicitly asks for a collection operation.

External sources (MCP connectors): If the content comes from a connected system (Google Drive, Notion, etc.), the same modes apply. Fetch individual docs for integrate/wrap/catalog. For large collections, use map mode — create a reference data point instead of copying everything locally.

Temporal check — is this about now or the future?

If the content made it to Step 2, the user chose "integrate." But double-check the temporal signals:

Signal in the content	Action
"We currently...", "Our pricing is...", "We serve..."	Integrate into active docs (proceed to Step 3)
"We plan to...", "Next quarter...", "We're considering..."	Stop. This belongs in `docs/_planned/`, not active docs. Route back to Step 1 triage as a planned deposit.
"We used to...", "Previously...", "Before the pivot..."	May update `_archive/` or inform an active doc's Context section

Important: Do not merge future-state content into an active document without discussing with the user.

Step 3: Find the Owner

Pre-read (cheap, do this first): if docs/document-index.md exists, read it before scanning individual files. It is the canonical inventory — one file lists every active data point, its DOMAIN, EXCLUSIVELY_OWNS, and cluster. Use it to narrow candidates to 1-3 likely owners; only then open those files. This avoids the grep-every-file failure mode and is dramatically cheaper than discovering ownership one file at a time.

If document-index.md does not exist yet (early-stage repo), use /context search <topic> to rank candidate owners via the canonical index. Fall through to per-file reading only if both are unavailable.

For each piece of knowledge:

Check existing data points — does one already OWN this topic?
- Use the document-index / /context search shortlist from the pre-read
- Read the EXCLUSIVELY_OWNS section of candidate data points
- If a clear owner exists → route there
Check STRICTLY_AVOIDS — make sure you're not putting it in the wrong place
- If data point X says "STRICTLY_AVOIDS competitor analysis" → don't put competitor info there
No owner found? → Recommend creating a new data point
- Suggest a name, cluster, and initial DOMAIN
- Use the template from docs/_bcos-framework/templates/context-data-point.md

Step 4: Integrate

For each affected data point:

Read the current content of the owning data point
Merge the new knowledge into the appropriate section:
- New facts → Content section
- New strategic implications → Context section
- Source info → Sources section (if it exists)
Check for contradictions with existing content:
- If the new info contradicts existing content → flag it, don't silently overwrite
- Present both versions to the user and ask which is current
Update metadata:
- Bump version (at least patch)
- Update last-updated to today
- Never touch created
- Keep or add useful tags for search/dashboard/Galaxy filtering
- Do not set last-reviewed for a content edit unless the doc was also checked and confirmed as current; use last-reviewed for validation without content mutation

Step 5: Update Cross-References

After integrating:

Check relationships — does this new knowledge affect other data points?
- If market context changed → competitive positioning may need review
- If audience changed → messaging and value prop may need review
Update BUILDS_ON / REFERENCES / PROVIDES if new connections emerged
Update Document Index (docs/document-index.md) if it exists:
- Run python .claude/scripts/build_document_index.py after material changes
- This also refreshes .claude/quality/context-index.json, the machine-readable index used by automations, dashboard, Galaxy, search, and filtering

Step 6: Report

Summarize what happened:

## Ingest Summary

**Source:** [what was ingested]
**Date:** [today]

### Updates Made
- **[data-point-name]** (v1.2.0 → v1.3.0): Added [what]
- **[data-point-name]** (v2.0.1 → v2.0.2): Updated [what]

### Contradictions Found
- [data-point]: new info says X, existing content says Y → [resolved/flagged]

### New Data Points Recommended
- [suggested name]: [why needed]

### Cross-References Updated
- [data-point-A] now REFERENCES [data-point-B]

### Document Index
- [Updated / No changes needed]

Handling Contradictions

When new information contradicts existing content:

Don't silently overwrite. The existing content may be deliberately different.
Present both versions to the user:
- "Your market-context data point says X. The new source says Y. Which is current?"
If user confirms the new version: Update the data point, note the change in the changelog.
If user says 'keep both': Note the contradiction in the Context section as a known tension.
If user is unsure: Flag the data point as status: under-review.

Batch Ingest

For multiple sources at once:

List all sources first
Classify each one
Group by target data point
Process one data point at a time (merge all relevant sources into it)
Report all changes at the end

Recommendation: Ingest one source at a time when possible. Stay involved. Check the summaries. Guide emphasis. Batch ingest is faster but less supervised.

Source Citation

When integrating new knowledge, preserve where it came from:

## Sources

| Claim | Source | Date | Confidence |
|-------|--------|------|------------|
| Market growing 15% YoY | Industry Report 2026 | 2026-03-15 | High |
| Competitor X raised Series B | TechCrunch article | 2026-04-01 | High |
| Customer segment shifting to enterprise | Q1 sales review | 2026-04-05 | Medium |

Not every claim needs a source. Use this for important facts, statistics, and claims that might be challenged or need periodic verification.

Automatic Handoffs

After ingest completes, automatically do these (don't wait for the user to ask):

→ Rebuild Document Index — Always: python .claude/scripts/build_document_index.py
→ Update current-state.md — If the ingested content is significant, offer to update "What Changed Recently"
→ context-audit — If a new data point was created: "Want me to run a quick CLEAR audit on the new doc?"

Integration with Other Skills

Skill	How It Connects
context-onboarding	Onboarding discovers what exists; ingest adds new knowledge to it
context-audit	After ingest, audit catches any boundary violations introduced
daydream	Reflection may reveal knowledge gaps; ingest fills them
core-discipline	Compounding rule triggers ingest: "file this insight back into context"
clear-planner	Large ingests (10+ sources) may need a plan first
bcos-wiki	Wiki-promotion route for explanatory pages, source summaries, and direct `/wiki promote` or `/wiki create` handoff
lifecycle-sweep (job)	Consumes the `lifecycle:` frontmatter declared at capture time. Step 1.5 prompts for it on time-bounded content.

Architecture docs: For routing design context, see docs/_bcos-framework/architecture/content-routing.md

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)