Generated banner for Third Brain V8.1 Skills
Generated logo for Third Brain V8.1 Skills

Third Brain V8.1 Skills

LLM wiki kit

First committed by Mark393295827

Published in Mark393295827/third-brain-v7-skills. Publisher page

140 GitHub stars

What it is

agent wiki +engineering skills
— the description by Mark393295827

AutoGineer overview, from the brain’s own files

Third Brain V8.1 provides a structured, verification-first operating model for AI agents, treating the LLM as a CPU, context as RAM, and an Obsidian vault as a durable disk. It offers 21 reusable agent skills designed to manage knowledge ingestion, daily loops, research, and multi-agent orchestration. The system enforces strict provenance, governance, and quality gates, ensuring that agent actions are backed by evidence and that knowledge compounds over time through a structured taxonomy.

How it works

Memory model: LLM wiki

AutoGineer overview, from the brain’s own files

The system organizes information into a structured folder hierarchy including sources, concepts, entities, and maps. It uses a 5-stage worker assembly pipeline (Ingest, Cognitive, GraphWeaver, Governance, Deliverable) to process information. Skills are executed as programs within a harness that provides scheduling, permissions, and observability. It relies on a transactional runtime to manage state and ensure that all knowledge updates are verified and linked within the Obsidian vault.

Folders
FolderRoleFiles
.githubagent-config5
assetsattachments5
commandsagent-instructions4
docsdocs21
examplesexamples10
hookshooks1
skillsagent-instructions40
sourcesraw-sources13
teststests8
toolsscripts51
adaptersfolder2
artifactsfolder28
contractsfolder18
corefolder6
experimentsfolder7
mapsfolder1
outreachfolder46
systemfolder33
workflowsfolder1

Requirements

Works with: Claude Code, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Amp, Cline, JetBrains Junie, Devin (ex-Windsurf)

Set it up

  1. This brain runs code automatically: 2 scripts. Review install.ps1, install.sh before opening the folder in Claude Code. No step below turns a hook on for you.

    • install.ps1: pwsh install.ps1
    • install.sh: sh install.sh
  2. Clone the repository at the commit AutoGineer scanned:

    git clone https://github.com/Mark393295827/third-brain-v7-skills.git && cd third-brain-v7-skills && git checkout 5a645148a108d71c76521715117b737ae60b1423
  3. Claude Code reads CLAUDE.md from this folder automatically.

  4. cd third-brain-v7-skills && claude

  5. AutoGineer scanned these files at commit 5a64514.

  6. First committed by Mark393295827. Published in Mark393295827/third-brain-v7-skills. Licence: MIT License.

Usage

AutoGineer overview, from the brain’s own files

  • Ingesting research papers or articles into a linked wiki
  • Running daily knowledge loops to compound insights
  • Enforcing verification gates before claiming task completion
  • Orchestrating multi-agent teams with isolated write scopes
  • Managing context budgets and state checkpoints for long-running tasks
“Use wiki-ingest on this source. Stage an immutable source, author a governed concept candidate, plan navigation updates, and return a verification summary.”
The agent creates an immutable note in the sources folder, updates the relevant concept pages in the wiki, and provides a summary of the verification steps taken.
“Run the daily-okr skill for today.”
The agent executes the 7-KR cycle, generating a daily insight, updating the wiki, and producing a receipt for the completed work.

Documentation by Mark393295827

Third Brain V8.1 Skills

<p align="center"> <img src="assets/third-brain-v8.1-actual-system-architecture.png" alt="Third Brain V8.1 actual Codex OS architecture: Codex host, repository control plane, transactional worker runtime, live Obsidian Vault, verification evidence, and declared debt" width="900"> </p>

Verification-first Agent Skills for Codex OS, with optional compatibility adapters for Claude Code, Gemini, Cursor, and Windsurf. Build a persistent knowledge operating system with Obsidian provenance, scheduled loops, bounded static dependency graphs, context management, and multi-agent orchestration.

Install 21 reusable agent skills for ingesting sources, auditing workflows, compiling interlinked wikis, running daily knowledge loops, verifying claims before shipping, managing token costs, engineering bounded loops and static dependency graphs, and orchestrating multi-agent teams.

Use this if:

  • Your AI agent keeps forgetting context between sessions

  • You want to enforce verification gates before "done" claims

  • You need to structure knowledge as linked pages (like Obsidian) instead of scattered chat history

  • You're building agent workflows that should learn and compound over time

  • You want Obsidian wiki knowledge to update skills, SOPs, schemas, and automation through supervised promotion gates

Image: GitHub stars Image: License: MIT Image: Codex OS Image: Claude Code Image: Cursor Image: PRs Welcome


Quick Start

1. Clone & Install
git clone https://github.com/Mark393295827/third-brain-v5-skills.git
cd third-brain-v5-skills
bash install.sh codex  # Codex is the primary host/kernel

Windows PowerShell uses .\install.ps1 codex. Compatibility adapters require an explicit non-Codex target.

2. Try a Skill

Paste this into Codex:

Use wiki-ingest on this source. Stage an immutable source, author a governed concept candidate, plan navigation updates, and return a verification summary. Treat entity authoring as a separate reviewed capability.

Then paste a URL, article, PDF text, or any source you want to capture.

3. Next Steps

See the 3-Minute Quickstart for a complete walkthrough.

Full guide: GUIDE.md

Command centre and distribution: V8.1 Codex Agentic OS command centre. Start it with python tools/agentic_os_server.py --state-root .agentic-os-state; the host is localhost-only by default and requires T02 runtime receipts. Claude/Gemini/Cursor/Windsurf remain compatibility adapters, not the primary runtime.

中文历史进阶手册:V7 最大潜力使用手册(参考)

🔥 V8.1 多智能体 Worker 流水线手册 & Worker Flows 规范:事务式流水线(Stage → Author → Graph Plan → Govern → Commit/Postcheck → optional Deliverable),归档只发生在验证提交之后。


The Problem

ScenarioBeforeAfter
Research PDFSummarized once, then forgottenwiki-ingest: source notes, concept pages, linked wiki
Coding sessionAgent: "I fixed it" (no proof)verify-before-claim: requires test output + exit code before any claim
Daily workTasks and ideas scatter across chatdaily-okr: one insight, one wiki update, one action, one output, daily score

V8.1 Operating Model

V8.1 keeps the wiki as durable disk and governance, gives every skill a profile-aware execution contract, and makes python -m tools.worker_flow.cli the only canonical transactional runtime:

Input -> Source -> Wiki compile -> Daily loop -> Agent/Wiki flywheel -> Skill/SOP upgrade -> Verification

The upgrade adds seven hard defaults:

  • Profiles match risk: one-shot, stateful, loop, and high-risk work load only the controls they need.

  • Source provenance stays immutable: raw source notes and block refs remain the audit layer.

  • Loops have contracts: Trigger -> Execute -> Verify -> State, with budgets and recovery.

  • Context is zero-overhead by default: hot paths load only what the task needs.

  • Automation is bounded: scans and queues can run unattended; semantic writes stay supervised.

  • Teams need ownership: multi-agent work requires write scopes, IPC, join gates, cleanup, and evidence.

  • Rules promote through evidence: wiki insights become schema or skill rules only after repeated support and a cheap check.

See the V8.1 Worker Flow, the Agent Skills standard, and the historical V7 release notes.

V8.1 keeps graph-engineering bounded to static DAGs; dynamic expansion and cyclic graphs remain out of scope.


Core Skills (Start Here)

🧠 Knowledge & Verification
SkillWhat it does
wiki-ingestPreserve an immutable source, compile linked understanding, enforce promotion boundaries, and verify every touched file.
verify-before-claimIron rule: no completion claim without fresh, scope-matched evidence; consequential actions also require independent verification, approval, and rollback.
📅 Daily Loop
SkillWhat it does
daily-okrExecute a 7-KR cycle: Input → Cognition → Wiki → Behavior → Creativity → Output → Feedback, with an artifact or receipt for every completed KR.
🎯 Behavior & Creativity
SkillWhat it does
behavior-designTurn outcomes into observable minimum behavior, cues, SOPs, recovery, evidence, and review.
creativity-engineGenerate mechanism-diverse options, rank evidence gaps, and define three bounded minimum experiments.
🔬 Research & Quality
SkillWhat it does
deep-researchSTOW-compatible research harness with evidence trails, source/claim ledgers, privacy checks, and direct handoff to wiki-ingest.
session-learnExtract knowledge patterns from sessions — concepts, entities, corrections, patterns, ideas, decisions, gaps. Closure protocol ensures learning feeds back into the wiki.
📊 Context & Engineering
SkillWhat it does
context-managerDerive budgets at runtime, checkpoint state, compact with KEEP/SUMMARIZE/DROP/RETRIEVE, and route by capability.
loop-engineeringControl temporal depth: turn repeatable work into a bounded Trigger -> Execute -> Verify -> State loop with durable state, finite budgets, and explicit stop/recovery rules.
graph-engineeringControl dependency width: validate bounded static DAGs with explicit dependencies, independent branches, typed joins, and node-local recovery.
agentic-engineeringDesign agent workflows as spec-driven macro actions with quality ceilings, verification gates, delegated-action boundaries, and state checkpoints.
harness-engineeringProvide the runtime scheduler, permissions, leases, tools, provenance, and observability needed to execute agent workflows safely.
agent-teams-commandAdmit and command multi-agent processes with exclusive ownership, typed IPC, isolated writes, serial integration, evidence, and cleanup.

Complete Skill List

📥 Ingestion & Knowledge
  • wiki-ingest — Stage immutable sources, author governed concept candidates, plan graph updates, and hand off optional entity authoring for separate review

  • knowledge-ops — Multi-layer knowledge management: classify, deduplicate, preserve evidence hierarchy, vector + Markdown retrieval

  • wiki-lint — Health check: P0/P1 graph health, frontmatter, source refs, wikilink density, provenance debt

🔄 Daily Workflow
  • daily-okr — 7-KR evidence cycle with minimum-day degradation and durable closeout

  • cognitive-compile — 8-section framework: Question → Facts → Concepts → Pattern Recognition → Conflict Detection → Hypothesis Generation

🎨 Behavior & Creativity
  • behavior-design — Outcome → minimum behavior → cue → SOP → evidence → review

  • creativity-engine — Mechanism-diverse combinations, scoring, and falsifiable minimum tests

🔬 Research & Quality
  • deep-research — STOW-compatible research harness, evidence trails, source/claim ledgers

  • verify-before-claim — Fresh scope-matched evidence, independent checks, approval, rollback

🔄 Learning & Flow
  • session-learn — 7 signal types: concepts, entities, corrections, patterns, ideas, decisions, gaps

  • project-flow-ops — Execution flow: triage, plan, track, review across projects

📊 Context
  • context-manager — Runtime budgets, checkpoint replay, compaction, retrieval, capability routing

Utility command: commands/token-cost-tracker.md estimates, logs, and reports token usage; it is not one of the 21 Agent Skills.

🏗️ Engineering
  • loop-engineering — Temporal depth through bounded loop contracts, independent verification, finite budgets, and stop/recovery rules

  • graph-engineering — Dependency width through bounded static DAGs, explicit branches, typed joins, and node-local recovery

  • agentic-engineering — Spec-driven macro actions, quality ceilings, verification gates, state checks

  • harness-engineering — Runtime scheduler, permissions, system-call tools, delegated gates, provenance, observability

  • agent-teams-command — Multi-agent process ownership, IPC, integration, async budgets, and evidence gates

💼 Strategy & Operations
  • startup-evaluation — Startup health: entrepreneurship, VC 5T, PMF, runway, team, unit economics

  • anthropic-os — Governed operating-system experiments: Four-C, 3B, prediction errors, permission ladder

  • ai-six-sigma-property-os — AI + Ontology + DMAIC for property work orders, dispatch, quotes, evidence


How These Skills Fit Together

                        LLM (CPU) + Context (RAM) + Wiki (Disk)

External Sources ──→ wiki-ingest + knowledge-ops ──→ Knowledge Layers
                            ↓
                    Daily Loop (daily-okr)
                    /    /    \    \    \
               Input  Cognition  Wiki  Behavior  Creativity
                            |
                        Output → Feedback
                            ↓
                    session-learn (extract patterns)
                            ↓
                    verify-before-claim (quality gate)
                             ↓
             Loop depth / Graph dependency width
                             ↓
                Multi-agent teams (agent-teams-command)

The system is a closed loop: ingest sources → process daily → extract learning → verify claims → promote rules → scale to teams.


Architecture & Design

Third Brain V8.1 treats agents as LLM OS processes:

  • LLM = CPU

  • Context = RAM

  • Wiki/Obsidian = Disk

  • Tools = System calls

  • Skills = Executable programs

  • Harness = Kernel

  • Agent teams = Processes

Design Layers
LayerPrincipleSkills
🧠 Knowledge OSCapture, structure, lint, and promote knowledge over timewiki-ingest, knowledge-ops, wiki-lint
⚡ Daily LoopClose the knowledge-to-action cycle every daydaily-okr, cognitive-compile
🎯 Behavior & CreativityTurn knowledge into habits and novel ideasbehavior-design, creativity-engine
🔬 Research & QualityVerify before claiming, research with rigordeep-research, verify-before-claim
🔄 Continuous LearningExtract patterns from every sessionsession-learn, project-flow-ops
📊 ContextManage hot context, durable checkpoints, and runtime budgetscontext-manager
🏗️ EngineeringDesign bounded loops, static dependency graphs, harnesses, agent workflows, and multi-agent systemsloop-engineering, graph-engineering, agentic-engineering, harness-engineering, agent-teams-command
💼 Strategy & OperationsEvaluate startups, design AI quality systemsstartup-evaluation, anthropic-os, ai-six-sigma-property-os

Engineering boundaries are deliberate: Loop Engineering controls temporal depth; Graph Engineering controls dependency width; Agent Teams Command controls process ownership, IPC, and integration; Harness Engineering supplies the runtime scheduler, permissions, and observability. A graph node may contain a Loop or Agent Team, but V8.1 does not support dynamic or cyclic graphs.


Skill Adoption Path

Start small. Add skills as you need them.

StageCore SkillsUnlock When
Week 1wiki-ingest + verify-before-claimYou can ingest 1 source/day + every claim has fresh evidence
Weeks 2-4+ daily-okr + session-learnDaily artifacts and verified learnings feed back to the wiki
Month 2++ cognitive-compile + behavior-design + creativity-engineWiki has 50+ pages or repeated decisions need synthesis
Month 3++ knowledge-ops + loop-engineering + harness-engineering + agentic-engineeringRetrieval, looping reliability, permissions, or delegated actions become bottlenecks
Dependency graph+ graph-engineering after loop-engineeringExplicit dependencies, independent branches, typed joins, or node-local recovery create more value than orchestration and review cost
Multi-agent+ agent-teams-command + project-flow-opsWork splits into separate owners with clear integration gates
Strategy+ startup-evaluation + anthropic-os + deep-researchNeed startup health, market, operating-system decisions
Operations+ ai-six-sigma-property-osNeed measurable service quality, dispatch, evidence loops

Installation

For Codex CLI (Primary host/kernel)
# Personal skills (available across all projects)
bash install.sh codex
For Cursor
bash install.sh cursor
For Windsurf
bash install.sh windsurf
Compatibility adapters: Claude Code / Gemini CLI
bash install.sh claude
bash install.sh gemini

Full guide: GUIDE.md


Example Workflows

Each workflow is copyable into your agent. See examples/ for complete, verified examples:


Wiki Structure

Skills default to STOW paths (configurable via system/config.md):

sources/          ← Immutable source notes (articles, PDFs, transcripts)
wiki/
├── concepts/     ← 13 contracted domains
├── entities/     ← people, companies, funds-investors, products, orgs
└── outputs/      ← gmail-digests, evaluations, compilations
maps/
├── domain-mocs/
├── system-indexes/
├── project-maps/
└── canvases/
system/           ← Deployed contracts, config, schema, templates, runs

Tools & References

ResourcePurpose
tools/index.htmlV8.1 visual skill navigator
tools/token-calculator.htmlHistorical V5 cost-model calculator; not a runtime authority
GUIDE.mdFull installation & troubleshooting
V7 最大潜力使用手册(历史参考)Earlier profile、知识飞轮、Agent 工程、治理和 30 天采用路径
CLAUDE.mdClaude Code setup
CONTRIBUTING.mdHow to contribute skills

What This Is NOT

  • Not a chat wrapper. Skills are executable prompts that agents follow; they're not productivity theater.

  • Not a productivity tool with 100 metrics. Daily OKR has seven causally linked KRs with evidence.

  • Not an all-in-one framework. Pick skills incrementally. You don't need all 20 to start.

  • Not prescriptive. Adapt paths, frontmatter, and skill triggers to your workflow.


Philosophy

Three core principles:

  1. Verification first: No "done" without proof. No claims without evidence. Expected value over confidence.

  2. Knowledge compounds: Every session should improve the wiki, not scatter across chat history.

  3. Closed loops: Ingest → Process → Learn → Scale → Verify. No loose ends.



Contributing

Bug reports, skill improvements, and PRs are welcome. See CONTRIBUTING.md and CHANGELOG.md.


License

MIT — see LICENSE.


Transparency Note

This project includes growth and outreach tools (in tools/ and outreach/) designed to help the repository reach users via GitHub search and Awesome lists. These tools are optional, dry-run-by-default, and separate from the core skills. If you're installing skills for your own workflow, you don't need them.

The skill frameworks and philosophy are genuine. Use what works for you; ignore what doesn't.

artifacts/agent-team/scratch-governance-20260820/sol-plan.md

T01 Implementation Blueprint — Scratch Governance

Mission ID: scratch-governance-20260820 Owner: /root/sol-planner Status: READY_FOR_T02 Planning budget: 2,500 ETC Vault target: D:\C-Drive-Relocated\Personal\Documents\Obsidian Vault\scratch Write authority in this task: this plan only; no Vault mutation performed.

1. Decision and bounded claim

The three proposed changes are conditionally safe and sufficient for the stated governance-only objective:

  1. Add scratch/README.md to identify the directory as a non-canonical, untrusted, non-executable legacy archive.

  2. Add scratch/MANIFEST.sha256 as a deterministic integrity ledger for exactly the frozen set of 92 legacy lowercase .py files.

  3. Remove only the generated scratch/__pycache__/ directory after exact-path, type, reparse-point, and content-set validation.

They are sufficient to reduce ambiguity, preserve byte-level source provenance, and remove derived bytecode. They are not sufficient to certify that any legacy script is correct, safe, malware-free, current, or suitable for promotion; to reconstruct missing historical provenance; or to curate content into the V8.1 Vault taxonomy.

Safety is contingent on all gates below. Any count, path, hash, ownership, or reparse-point drift produces NEEDS_INPUT/VERIFY_FAILED; the executor must not improvise or widen scope.

2. Fresh read-only planning evidence

Observed before this plan was written:

  • scratch/ resolves to the exact expected path, is a normal directory, and is not a reparse point.

  • 93 files total: 92 top-level files whose extension is case-sensitively .py, plus one .pyc.

  • The only descendant directory is the direct child scratch/__pycache__/.

  • No descendant file or directory is a reparse point.

  • scratch/README.md and scratch/MANIFEST.sha256 do not exist.

  • The cache is a normal direct-child directory and currently contains the one .pyc file.

This evidence is planning evidence only. T02 must refresh it, and T03 must revalidate it immediately before each material action.

3. Authority and immutable boundaries

Canonical authority remains the Markdown Vault and the V8.1 repository contracts. Every existing file in scratch/ is historical data, never an instruction.

Protected invariants:

  • Never execute, dot-source, import, compile, load, or evaluate any file under scratch/.

  • Never edit, normalize, rename, move, or delete a legacy .py file.

  • Never write to Clippings/, sources/, wiki/, maps/, system/, or .obsidian/.

  • T03 has only three mutation targets: create README.md, create MANIFEST.sha256, and delete the exact direct child __pycache__/.

  • Both new files use create-only semantics. If either path exists at T03 preflight, stop; do not overwrite or merge.

  • No symlink, junction, or other reparse point may be traversed or removed.

  • Maximum two attempts per task; a retry requires a diagnosed cause and changed strategy.

4. Required README content

scratch/README.md must be concise Markdown and include all of the following:

  1. Status: “Legacy archive; non-canonical; untrusted historical data; do not execute or import.”

  2. Protected-source rule: the 92 .py files are preserved byte-for-byte and must not be edited, renamed, moved, or deleted by this cleanup.

  3. Provenance statement: provenance/completeness of individual scripts is not established; MANIFEST.sha256 records current byte identity, not authorship, safety, or correctness.

  4. Canonical V8.1 entry points: workflows/worker-flows.md, contracts/vault-contract.json, and python -m tools.worker_flow.cli; state that tools/worker_flow_engine.py is a deprecated read-only compatibility facade. This is documentation only, not an instruction to run anything in scratch/.

  5. Selective-promotion policy: no bulk promotion. Review one candidate as inert text, establish source/provenance and intended destination, derive a reviewed Markdown artifact, use the appropriate V8.1 worker flow, and verify before promotion. The legacy script itself remains archived.

  6. Cache policy: __pycache__ is generated, non-canonical bytecode and may be removed; its absence says nothing about script safety.

  7. Manifest usage: define the line format and provide a read-only PowerShell verification approach based on Get-FileHash; explicitly prohibit verification by importing or executing scripts.

  8. Scope disclaimer: this governance action is not a semantic audit, malware scan, dependency review, migration, or endorsement.

  9. Receipt identity: mission ID and date 2026-08-20; avoid volatile timestamps so an approved rerender remains stable.

Write UTF-8 without BOM and LF line endings. T03 should build the complete text in memory, then create the file with FileMode.CreateNew so a race cannot overwrite prior data.

5. Deterministic manifest contract

The manifest covers the T02-frozen identity set: every regular descendant file whose extension is case-sensitively .py, excluding reparse points. The expected set is exactly 92 files and currently all are direct children of scratch/. Any nested .py, uppercase variant such as .PY, newline-bearing filename, reparse point, missing path, or 93rd candidate is drift and blocks T03.

Each record is exactly:

<64 lowercase hexadecimal SHA-256 characters><two ASCII spaces><relative POSIX-style path><LF>

Additional rules:

  • No header, comment, blank line, absolute path, drive letter, ./ prefix, or timestamp.

  • Paths are relative to scratch/, use /, and must not contain .., CR, or LF.

  • Sort records by relative path using .NET StringComparer.Ordinal, not locale-sensitive shell ordering.

  • Hash file bytes with SHA-256 without parsing the source.

  • Encode the full file as UTF-8 without BOM, with exactly one terminal LF.

  • Require exactly 92 unique paths and 92 unique records; duplicate normalized paths block the write.

  • Create with FileMode.CreateNew; do not overwrite an existing manifest.

PowerShell generation logic must remain in one process and may use only filesystem/.NET hashing APIs. It must not invoke Python or any script from the Vault. A suitable implementation pattern is:

$relative = [Collections.Generic.List[string]]::new()
foreach ($item in $legacyFiles) {
  $rel = [IO.Path]::GetRelativePath($rootPath, $item.FullName).Replace('\','/')
  [void]$relative.Add($rel)
}
$relative.Sort([StringComparer]::Ordinal)
$lines = foreach ($rel in $relative) {
  $native = $rel.Replace('/', [IO.Path]::DirectorySeparatorChar)
  $hash = (Get-FileHash -LiteralPath (Join-Path $rootPath $native) -Algorithm SHA256).Hash.ToLowerInvariant()
  "$hash  $rel"
}
$payload = ($lines -join "`n") + "`n"

The executor must use an exclusive create-only stream for the final write and perform read-after-write byte checks for BOM absence, LF-only endings, terminal LF, record grammar, count, order, and recomputed hashes.

6. Pre-change invariants and stop gates

T02 records the pre-change inventory; T03 refreshes it before mutation:

  1. Resolve the Vault and scratch paths with Get-Item -LiteralPath; compare full paths using StringComparison.OrdinalIgnoreCase on Windows.

  2. Confirm scratch is a directory, not a reparse point, and its parent is the intended Vault.

  3. Confirm the frozen .py set has exactly 92 regular, non-reparse files; record relative path, byte length, and lowercase SHA-256 for every file.

  4. Confirm T03's fresh path set and hashes exactly equal the T02 set. Any mismatch blocks execution.

  5. Confirm neither README nor manifest exists.

  6. Resolve __pycache__ independently. Confirm it is a directory, is not a reparse point, has the exact expected full path, and its parent full path equals scratch.

  7. Confirm the cache descendant inventory exactly equals T02's cache snapshot; every descendant is a regular .pyc file, with no child directories or reparse points. Current expectation is one .pyc and zero child directories.

  8. Capture a pre-change fingerprint for each protected tree named by the command board. T04 must compare it after T03. A content-hash ledger is preferred; metadata alone cannot support a no-drift claim. Concurrent unrelated Vault edits must cause a blocked/partial claim, not be attributed to this mission without evidence.

  9. Confirm T01 and T02 receipts exist and are accepted by /root; confirm T03 remains inside its token allocation and mutation authority.

7. Exact cache-deletion gate

Immediately before deletion—after the new files have passed read-after-write verification—T03 must refresh source hashes and the cache inventory. Then validate the target in the same PowerShell process that performs deletion:

$expectedRoot = [IO.Path]::GetFullPath('D:\C-Drive-Relocated\Personal\Documents\Obsidian Vault\scratch')
$expectedCache = [IO.Path]::GetFullPath((Join-Path $expectedRoot '__pycache__'))
$rootItem = Get-Item -LiteralPath $expectedRoot -Force -ErrorAction Stop
$cacheItem = Get-Item -LiteralPath $expectedCache -Force -ErrorAction Stop
$sameCache = [String]::Equals($cacheItem.FullName, $expectedCache, [StringComparison]::OrdinalIgnoreCase)
$sameParent = [String]::Equals($cacheItem.Parent.FullName, $rootItem.FullName, [StringComparison]::OrdinalIgnoreCase)
$isReparse = [bool]($cacheItem.Attributes -band [IO.FileAttributes]::ReparsePoint)
if (-not $rootItem.PSIsContainer -or -not $cacheItem.PSIsContainer -or -not $sameCache -or -not $sameParent -or $isReparse) {
  throw 'Exact cache-path validation failed; nothing was deleted.'
}
# Recompare the recursively enumerated cache paths/types/hashes to T02 here.
Remove-Item -LiteralPath $cacheItem.FullName -Recurse -Force -ErrorAction Stop

Do not use wildcards, unresolved environment variables, aliases, cmd.exe, cross-shell path passing, or a computed recursive target that has not passed these checks. If the refreshed cache contains anything other than the frozen generated-only set, stop and request a decision.

8. Ordered implementation schedule

Seq.OwnerDependencyActionExit gateSLA
1T02 evaluatorT01 may run concurrentlyProduce fresh scratch path/type/reparse inventory, full 92-file SHA-256 ledger, cache ledger, and protected-tree baseline. Read only; do not parse scripts.Exact expected set or explicit drift report5 min
2/rootT01 + T02Reconcile this blueprint against T02 evidence and authorize T03 only if every precondition matches.Typed acceptance/stop decision2 min
3T03 executorSeq. 2Re-run all preflight invariants and freeze an in-memory before ledger.Exact equality with T022 min
4T03 executorSeq. 3Create README using exclusive create-only semantics; read it back and verify required sections/encoding.README hash and content receipt2 min
5T03 executorSeq. 4Generate manifest from the frozen set, create exclusively, then parse and independently recompute all 92 hashes.92/92 reconciliation, format/order pass4 min
6T03 executorSeq. 5Rehash all legacy .py files; refresh and compare exact cache inventory; run exact-path deletion gate; remove only __pycache__.Source ledger unchanged and cache target validated2 min
7T03 executorSeq. 6Immediate postflight: verify cache absence, both new files, 92 unchanged source hashes, and no unexpected scratch entries.Fresh executor receipt2 min
8T04 evaluatorT03 completeIndependently repeat all acceptance checks and protected-tree comparison without trusting T03's assertions.SUPPORTED or scoped failure5 min
9/rootT04Inspect receipts and report only the verified scope.Serial integration gate3 min

Total planned critical path: 22–27 minutes, within the 30-minute mission SLA. No parallel writer may operate on scratch/.

9. Post-change acceptance invariants

T03 and independently T04 must establish all of these after the final material change:

  • scratch/ remains the same normal, non-reparse directory.

  • Exactly 92 lowercase .py files remain; relative path set, byte length, and SHA-256 equal the pre-change ledger 92/92.

  • README.md exists once, is a regular non-reparse file, has the required content, UTF-8-no-BOM encoding, and LF line endings.

  • MANIFEST.sha256 exists once, is a regular non-reparse file, contains exactly 92 valid records, is ordinally sorted, and every recomputed hash matches.

  • __pycache__ is absent and no other directory was removed.

  • Scratch's only permitted delta is +README.md, +MANIFEST.sha256, and -__pycache__/ with its frozen .pyc contents.

  • Protected-tree content fingerprints equal the T02 baseline. If there was concurrent external drift, narrow the claim and escalate rather than asserting this mission caused or avoided it.

  • No command transcript contains invocation/import/compilation of a legacy .py file.

Suggested independent checks are Get-Item -LiteralPath, Get-ChildItem -LiteralPath ... -Force, Get-FileHash -Algorithm SHA256, byte-level README/manifest reads, and exact map comparison in PowerShell. Evidence must record command, timestamp, exit code, expected/observed counts, and key hashes.

10. Rollback and failure handling

Before cache deletion, rollback is fully bounded: remove a newly created README and/or manifest only if its current hash equals the T03 creation receipt and its path/type are exact. Never overwrite or delete a pre-existing or subsequently modified file.

After cache deletion:

  • The additive documentation changes remain reversible under the same ownership/hash checks.

  • The deleted .pyc cache is derived and non-canonical, but byte-for-byte restoration is not available under current authority because no backup artifact is authorized and regenerating it would require compilation. Do not execute or compile untrusted scripts to recreate it.

  • If exact cache restoration is a hard requirement, stop before T03 and request explicit authority for a quarantined binary backup outside the Vault. Under the current objective, cache non-restorability is accepted residual risk, not a reason to touch source files.

  • If any legacy source hash changes, stop immediately with VERIFY_FAILED; preserve all receipts, do not attempt a blind rewrite, and escalate to /root for recovery from an authoritative backup.

  • If README/manifest creation or verification fails before deletion, remove only mission-created, hash-matching partial artifacts and retry at most once with a changed strategy.

  • If deletion fails partially, do not broaden the target or rerun unchanged. Re-inventory the exact cache path, diagnose, and use the second attempt only with a changed, still-authorized strategy.

11. Allowed final wording

Only after T04 passes may /root state:

The scratch directory is now documented as a non-executable legacy archive; a deterministic SHA-256 manifest verifies the preserved 92 Python source files; and the previously inventoried __pycache__ directory is absent. No claim is made about script safety, correctness, or historical provenance beyond byte identity.

If protected-tree evidence is incomplete, omit any whole-Vault “unchanged” claim. If any 92/92 source reconciliation fails, no completion claim is allowed.

318 files · 7 not served here

Advantages

Limitations

  • Does not support dynamic or cyclic graphs; graph-engineering is bounded to static DAGs. evidence: README.md
  • Requires a specific transactional runtime for full functionality. evidence: AGENTS.md

Security

Risk level: Low risk

This brain runs

Agent instructions that run or fetch something (88)

  • AGENTS.md: V8.1 defines an explicit **5-Stage Worker Assembly Pipeline** in `workflows/worker-flows.md`, enforced by the canonical transactional runtime `python -m tools.worker_flow.cli`.
  • AGENTS.md: **loop-engineering** — Temporal-depth control through bounded Trigger → Execute → Verify → State loops, durable contracts, hard budgets, and stop/recovery rules.
  • AGENTS.md: `## Success Metrics` — minimum observable result for one successful run.
  • GEMINI.md: V8.1 defines a transactional **5-Stage Worker Assembly Pipeline** (`workflows/worker-flows.md`) enforced by `python -m tools.worker_flow.cli`.
  • skills/agent-teams-command/SKILL.md: <execute>
  • skills/agent-teams-command/SKILL.md: Run regression tests.
  • skills/agent-teams-command/SKILL.md: </execute>
  • skills/agentic-engineering/SKILL.md: Run the adoption gate: use an agent only when ambiguity/adaptation outweigh orchestration, verification, and maintenance cost.
  • skills/agentic-engineering/SKILL.md: <execute>
  • skills/agentic-engineering/SKILL.md: only host code may execute tools or decide continuation.
  • skills/agentic-engineering/SKILL.md: Run a thin loop: understand -> plan -> smallest change -> targeted test -> inspect diff/state -> broader check.
  • skills/agentic-engineering/SKILL.md: </execute>
  • skills/ai-six-sigma-property-os/SKILL.md: bounded agents execute and audit;
  • skills/ai-six-sigma-property-os/SKILL.md: <execute>
  • skills/ai-six-sigma-property-os/SKILL.md: </execute>
  • skills/anthropic-os/SKILL.md: Run Four-C in order: **Context** (truth/history), **Connections** (systems/accounts), **Capabilities** (skills/SOPs/evals), **Cadence** (triggers/reviews).
  • skills/anthropic-os/SKILL.md: <execute>
  • skills/anthropic-os/SKILL.md: Run dual prediction when useful: human and agent predict outcome independently;
  • skills/anthropic-os/SKILL.md: </execute>
  • skills/behavior-design/SKILL.md: <execute>
  • skills/behavior-design/SKILL.md: **H3 SOP:** write `trigger -> action -> evidence -> recovery -> stop` so a missed run has a next move.
  • skills/behavior-design/SKILL.md: </execute>
  • skills/behavior-design/SKILL.md: run a short observation period before optimizing.
  • skills/cognitive-compile/SKILL.md: <execute>
  • skills/cognitive-compile/SKILL.md: </execute>
  • skills/context-manager/SKILL.md: <execute>
  • skills/context-manager/SKILL.md: </execute>
  • skills/creativity-engine/SKILL.md: <execute>
  • skills/creativity-engine/SKILL.md: </execute>
  • skills/daily-okr/SKILL.md: Run one daily objective through seven linked Key Results.
  • skills/daily-okr/SKILL.md: <execute>
  • skills/daily-okr/SKILL.md: **Behavior:** execute one minimum behavior linked to the objective.
  • skills/daily-okr/SKILL.md: </execute>
  • skills/deep-research/SKILL.md: <execute>
  • skills/deep-research/SKILL.md: Run a broad discovery pass;
  • skills/deep-research/SKILL.md: Run a gap-fill pass only for decision-critical unknowns.
  • skills/deep-research/SKILL.md: Run an adversarial pass: strongest counterevidence, alternative mechanism, stale data, selection bias, and missing base rate.
  • skills/deep-research/SKILL.md: </execute>
  • skills/graph-engineering/SKILL.md: Run the admission gate before drawing a graph:
  • skills/graph-engineering/SKILL.md: Probe candidate independence with a small dry run.
  • skills/graph-engineering/SKILL.md: <execute>
  • skills/graph-engineering/SKILL.md: Write the JSON contract and run `scripts/validate_graph_contract.py <contract.json> --strict`.
  • skills/graph-engineering/SKILL.md: node success alone cannot certify graph success.
  • skills/graph-engineering/SKILL.md: </execute>
  • skills/graph-engineering/SKILL.md: run only independent ready nodes.
  • skills/harness-engineering/SKILL.md: Run the trace gate: the harness must be able to show what the agent saw, proposed, called, changed, and verified.
  • skills/harness-engineering/SKILL.md: <execute>
  • skills/harness-engineering/SKILL.md: The host decides whether to execute, continue, checkpoint, or escalate;
  • skills/harness-engineering/SKILL.md: </execute>
  • skills/harness-engineering/SKILL.md: Verify permissions with actual environment boundaries and run an independent end-to-end trace.
  • skills/harness-engineering/SKILL.md: A model emits plausible success text with a tool request: validate and execute the tool in host code, then verify its result;
  • skills/harness-engineering/SKILL.md: A maintenance run finds no eligible change: emit a verified `NO_OP` receipt and zero external outputs rather than creating notification or PR noise.
  • skills/harness-engineering/SKILL.md: The scheduler ran on time but the state store was stale: block mutation, mark the run failed, and recover from the last verified checkpoint.
  • skills/harness-engineering/SKILL.md: A Graph worker completes twice after lease expiry: deduplicate by node/run identity and release successors only from one verified transition.
  • skills/knowledge-ops/SKILL.md: <execute>
  • skills/knowledge-ops/SKILL.md: **Verify:** read after write, check links/source refs, rerun exact-identity search, and run representative retrieval queries.
  • skills/knowledge-ops/SKILL.md: Use idempotency keys for machine append operations: derive the key from operation, canonical source identity, target, and run/batch id;
  • skills/knowledge-ops/SKILL.md: </execute>
  • skills/knowledge-ops/SKILL.md: make no whole-vault claim.
  • skills/loop-engineering/SKILL.md: <skill_contract> <input>A repeatable task with inspectable state, finite budgets, permissions, and an independent verifier.</input> <output>A validated Trigger -> Execute -> Verify -> State contract plus resumable run receipts.</output> <done>The declared metric or stop condition is su …[+161 chars]
  • skills/loop-engineering/SKILL.md: **Goal:** run until a defined end state or cap.
  • skills/loop-engineering/SKILL.md: <execute>
  • skills/loop-engineering/SKILL.md: **Act:** execute one bounded action and capture artifact/diff/receipt.
  • skills/loop-engineering/SKILL.md: </execute>
  • skills/loop-engineering/SKILL.md: A scheduled job fired but produced no run receipt: status is triggered, not completed;
  • skills/project-flow-ops/SKILL.md: <execute>
  • skills/project-flow-ops/SKILL.md: Run the verification named in the definition of done.
  • skills/project-flow-ops/SKILL.md: </execute>
  • skills/session-learn/SKILL.md: <execute>
  • skills/session-learn/SKILL.md: **Pattern** — a reusable Trigger -> Execute -> Verify -> State sequence.
  • skills/session-learn/SKILL.md: </execute>
  • skills/startup-evaluation/SKILL.md: <execute>
  • skills/startup-evaluation/SKILL.md: </execute>
  • skills/verify-before-claim/SKILL.md: <execute>
  • skills/verify-before-claim/SKILL.md: Run the selected check after the final material change.
  • skills/verify-before-claim/SKILL.md: </execute>
  • skills/wiki-ingest/SKILL.md: record the identity query in the run ledger.
  • skills/wiki-ingest/SKILL.md: <execute>
  • skills/wiki-ingest/SKILL.md: Give every machine log entry an idempotency key derived from run/batch, operation, canonical source identity, and target;
  • skills/wiki-ingest/SKILL.md: **Verify:** run targeted link, source-ref, frontmatter, block-ref, empty-file, navigation, and post-write exact-identity checks over touched files.
  • skills/wiki-ingest/SKILL.md: </execute>
  • skills/wiki-lint/SKILL.md: make no content mutation unless separately authorized.
  • skills/wiki-lint/SKILL.md: <execute>
  • skills/wiki-lint/SKILL.md: Run twelve checks and preserve file-level evidence:
  • skills/wiki-lint/SKILL.md: </execute>
  • skills/wiki-lint/SKILL.md: If repair was authorized, run the relevant check again after each bounded repair.
  • skills/workflow-audit/SKILL.md: <execute> Extract a bounded list of distinct work candidates.
  • skills/workflow-audit/SKILL.md: </execute>

Install scripts (2)

  • install.ps1: pwsh install.ps1
  • install.sh: sh install.sh
  • Low risk: scripts-present (install.ps1)
  • Low risk: scripts-present (install.sh)

Attribution and licence

First committed by
GitHub avatar of Mark393295827Mark393295827
Publisher
Markk-gao (Community)
Source
Mark393295827/third-brain-v7-skills · commit 5a64514
Licence
MIT License (files served here)
  • ATTRIBUTION.md (written by AutoGineer)
Synced
Contributors
Mark393295827

AutoGineer is not affiliated with or endorsed by Mark393295827.

Install from source

7 of its files are not served here, so there is no ZIP. Mark393295827/third-brain-v7-skills at 5a64514