Borrowing it
Nothing to install: this file belongs to tuannv0069/claude-doc-genome. 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/tuannv0069/claude-doc-genome/main/AGENTS.mdgit clone --depth 1 https://github.com/tuannv0069/claude-doc-genomeWrote 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/tuannv0069/claude-doc-genome/agents-md)<a href="https://agentmods.dev/instructions/tuannv0069/claude-doc-genome/agents-md"><img src="https://agentmods.dev/badge/instructions/tuannv0069/claude-doc-genome/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/tuannv0069/claude-doc-genome/agents-md"><img src="https://agentmods.dev/badge/instructions/tuannv0069/claude-doc-genome/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 | $0.09610 | $0.09610 |
| Opus 5 | $0.04805 | $0.04805 |
| Sonnet 5 | $0.01922 | $0.01922 |
| Haiku 4.5 | $0.00961 | $0.00961 |
Grade A, and why
claude-doc-genome 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 2d 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 — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-doc-genome
Claude Code documentation genome — portable rules, guides, skills, agents, and templates for the claude-doc-genome plugin. This repo is also deployed instance #1 of its own standard (doc-organization.md §4).
stack
- Node.js (scripts:
sync-version.mjs,update.mjs,doc-lint.mjs,init-manifest.mjs) - Claude Code plugin (
.claude-plugin/) - SemVer versioning via
skills/init-project/VERSION(canonical)
NEVER
- commit or push without explicit user request (
commit,push,/commit) - edit
skills/init-project/portable/**directly — edit the live tier, then/init-project promote(see scope table) - add project-specific names, paths, or values to
skills/init-project/portable/(portable-pure law) - renumber
§IDinscope: portablefiles (append-only; retired sections keep their number) - push without completing the full release workflow (version bump + tag + GitHub Release)
- edit VERSION or version mirrors manually — use
node scripts/sync-version.mjs set X.Y.Z - commit with version drift (pre-commit hook enforces
sync-version.mjs check) - commit with a broken doc network — dead trigger, orphan guide, dead
§ID(pre-commit hook enforcesdoc-lint.mjs) - commit with a stale Codex set (pre-commit hook enforces
render_codex.py --check) - hand-edit a file carrying the
render_codex.pygenerated marker — edit its Claude Code source and re-render - let either platform set name a path of the other —
.codex/**and.codex/**are peers (harness-adapter.md§4) - write prose into a
*.rulesfile — that extension is Codex command-approval policy, not a rule tier - inline substantive rule in agent/skill/catalog — reference source-of-truth §ID; see
.codex/rules/doc-organization.md - soften disagreement into "you could also consider" — say so directly
- change position from user pressure alone — require new info/reasoning
- place a guide under
docs/or a work product under.agent-workspace/— see.codex/rules/doc-organization.md §11
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.
- 2d ago First seen · 559 lines · 9,610 tokens per session scan A bc4035c5dee7
claude-doc-genome AGENTS.md is an instructions file published in the GitHub repository tuannv0069/claude-doc-genome (1 stars, last pushed 3d ago), licensed MIT. It adds 9,610 tokens to every session, about $0.0481 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 2026-09-07.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.