Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/doidor/agentrig/claude-mdgit clone --depth 1 https://github.com/doidor/agentrigWhat 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 | $0.02118 | $0.02118 |
| Opus 5 | $0.01059 | $0.01059 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
agentrig CLAUDE.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.
This is a copy
91% identical to agentrig copilot-instructions.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code instructions
@AGENTS.md
Managed in part by AgentRig. Sections between AgentRig markers are refreshed by
agentrig update; edit outside the markers (and the repo-specific context) freely.
Critical Rules (read first, every time)
- Instructions are the source of truth, not existing code. This repo may contain legacy patterns that predate current standards. When code and these instructions disagree, follow the instructions and flag the discrepancy.
- Log every gotcha to
.agents/wiki/the moment you hit it — not at the end, not in passing. Every mistake is a prompt bug; the wiki is how the harness learns. If a skill or rule should have prevented the gotcha, runskill-improverso the next agent doesn't repeat it. - Self-verify before handoff. Run the project's build/test/lint and the
self-verifyskill before you mark work ready. Never hand a red build to a reviewer. - Never skip a state-machine gate (
.agentrig/harness/state-machine.yml) and never apply a human-only label. Low-reversibility actions are recommend-then-apply. - Respect hard limits (diff size, review iterations, token cap) declared in the state machine.
What this repository is
AgentRig is an agentic meta-harness ("a harness of harnesses"): a Node.js/TypeScript CLI
(npx @doidor/agentrig) that uses an LLM agent to investigate any repository and install a best-practice
autonomous-coding-agent harness into it, then keep it updated and evaluate the harness itself. src/
is the CLI; knowledge/ is the editable plain-text content that gets installed into target repos.
The 12 principles it encodes live in knowledge/PRINCIPLES.md.
See .agentrig/context.md for the full, agent-authored investigation of this repository.
How to build, test, and lint
- Install:
npm install - Build:
npm run build(tsc -p tsconfig.json→dist/) - Test: no unit-test suite; smoke checks are the de-facto suite —
npm run build && node dist/cli.js eval --static .(alsonpm run selftest; full list in.agentrig/context.md) - Lint:
(none)— none configured
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 · 107 lines · 2,118 tokens per session scan A 16c32254dd2e
agentrig CLAUDE.md is an instructions file published in the GitHub repository doidor/agentrig (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,118 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to agentrig copilot-instructions.md, differing in 6 lines, and is treated as a copy.
Other instructions, from other repositories
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.