Borrowing it
Nothing to install: this file belongs to jason21wc/ai-governance-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jason21wc/ai-governance-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/jason21wc/ai-governance-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/jason21wc/ai-governance-mcp/agents-md)<a href="https://agentmods.dev/instructions/jason21wc/ai-governance-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jason21wc/ai-governance-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jason21wc/ai-governance-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jason21wc/ai-governance-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02939 | $0.02939 |
| Opus 5 | $0.01470 | $0.01470 |
| Sonnet 5 | $0.00588 | $0.00588 |
| Haiku 4.5 | $0.00294 | $0.00294 |
Grade A, and why
ai-governance-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Governance MCP Server
Description: Semantic retrieval system for AI governance principles and methods. Framework: AI Coding Methods Mode: Standard
Memory Files
Memory files live in _ai-context/ (unified layout, v2.62.0 session-243 migration — nothing auto-discovers them; this loader is the pointer):
| File | Purpose |
|---|---|
| _ai-context/SESSION-STATE.md | Current position, next actions |
| _ai-context/BACKLOG.md | Discrete projects (start, work, finish) |
| _ai-context/OPERATIONS.md | Recurring operational commitments (cadences, tripwires, metrics) |
| _ai-context/PROJECT-MEMORY.md | Decisions, constraints, gates |
| _ai-context/LEARNING-LOG.md | Lessons learned |
| _ai-context/SESSION-HANDOFF.md | Channel between a two-session IMPLEMENTER/VERIFIER split. Not a memory file — a transient protocol channel; read it only when running that split. Scope question filed as BACKLOG #233. |
| ARCHITECTURE.md | System design, data flow (structural doc — stays at root) |
.claude/skills/completion-sequence-aigov/ |
Post-change steps including rename procedure for principle ID changes (invoke via /completion-sequence-aigov) |
.claude/skills/compliance-review/ |
Periodic governance health (invoke via /compliance-review) |
Data that is NOT in this repo (session-268). The Reference Library and the search index are user data / build artifacts and live outside the checkout — ~/dev-tools/reference-library/ and ~/.ai-governance/index/ on this machine, ~/.ai-governance/ by default for anyone else. index/ and reference-library/ are gitignored, so their absence from git status is correct. Rebuild the index with python -m ai_governance_mcp.extractor after changing documents/; nothing does it automatically. That command needs an interpreter carrying sentence-transformers, and python may not be it. Measured 2026-08-30 on this machine: python resolves to /opt/anaconda3/bin/python3, which has it, while the project's own .venv/bin/python does not — so the documented command works by PATH ordering, not by design. The extractor now names the running interpreter and the fix when the import fails, instead of raising a bare ModuleNotFoundError. It also retries a failed model load with local_files_only=True, because sentence-transformers contacts Hugging Face for repo metadata even when every weight is cached, and a transient 403 should not fail a rebuild that needs nothing from the network. Also pass the reference-library path — the MCP host injects it and a shell does not inherit it: AI_GOVERNANCE_REFERENCE_LIBRARY_PATH=$(python3 scripts/resolve_reference_library.py | head -1 | cut -d= -f2), or the shrink guard will refuse the build (correctly). Rationale + settings: ARCHITECTURE.md → "Data that lives outside the checkout".
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 101 lines · 2,939 tokens per session scan A 0134bcd2a61f
ai-governance-mcp AGENTS.md is an instructions file published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2,939 tokens to every session, about $0.0147 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.