agentmods.dev

crag AGENTS.md

A repository instruction file for crag, a tool that turns one governance file into instructions for coding agents and development checks.

In plain words
What is it for?
Use it when working on crag to run its required tests and checks, follow its Node.js conventions, and understand where its source, commands, documentation, and tests live.
Why use it?
It gives agents shared rules and records the tests, build checks, coding style, and project layout they must follow.

Instructions file for CodexOpenCode

40 1mo ago A scan 534 tokens original Apache-2.0
View the source file WhitehatD/crag
Install

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.

agentmods
npx agentmods add instructions/whitehatd/crag/agents-md
Clone the repo
git clone --depth 1 https://github.com/WhitehatD/crag

Made for: Codex, OpenCode.

Per session 534 This file is loaded in full into every session.
When invoked 534 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00534 $0.00534
Opus 5 $0.00267 $0.00267
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 2d ago against content hash 54cd3f48c5b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crag 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.

AGENTS.md · 74 lines

What it actually says

AGENTS.md

Generated from governance.md by crag. Regenerate: crag compile --target agents-md

Project: @whitehatd/crag

Make every AI agent obey your codebase. One governance.md → compiled to CI, hooks, and every agent. No drift.

Quality Gates

All changes must pass these checks before commit:

Test

  1. node test/all.js

Build

  1. node --check bin/crag.js
  2. node --check bin/crag-mcp.js

Ci (inferred from workflow)

  1. node bin/crag.js help > /dev/null
  2. node bin/crag.js version
  3. node bin/crag.js analyze --dry-run > /dev/null
  4. node bin/crag.js upgrade --check > /dev/null
  5. node bin/crag.js workspace --json > /dev/null

Coding Standards

  • Stack: node
  • Conventional commits (feat:, fix:, docs:, etc.)
  • Commit trailer: Co-Authored-By: Claude [email protected]

Architecture

  • Type: cli
  • Entry: bin/crag.js, bin/crag-mcp.js

Key Directories

  • .circleci/ — CI/CD
  • .github/ — CI/CD
  • assets/ — static assets
  • bin/ — executables
  • docs/ — documentation
  • scripts/ — tooling
  • src/ — source
  • test/ — tests

Code Style

  • Indent: 2 spaces

Anti-Patterns

Do not:

  • Do not write absolute local paths in governance (e.g. D:/project/src/) — use relative paths only (e.g. src/). Governance files are checked into the repo and must remain portable across machines.
  • Do not leave console.log in production code — use a proper logger
  • Do not use synchronous filesystem APIs in request handlers

Security

  • No hardcoded secrets — grep for sk_live, AKIA, password= before commit

Workflow

  1. Read AGENTS.md at the start of every session — it is the single source of truth.
  2. Run all mandatory quality gates before committing.
  3. If a gate fails, fix the issue and re-run only the failed gate.
  4. Use the project commit conventions for all changes.
Changes

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.

  1. 2d ago First seen · 74 lines · 534 tokens per session scan A 54cd3f48c5b5

Subscribe to this mod's changes

crag AGENTS.md is an instructions file published in the GitHub repository WhitehatD/crag (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 534 tokens to every session, about $0.0027 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 2026-08-30.

Workflow Automationai-agentsclaude-codedeveloper-toolsmeta-frameworkself-improving
Related

Other instructions, from other repositories

n8n-skills CLAUDE.md

Instructions for czlonkowski/n8n-skills, covering claude.md, project overview, repository structure, the 14 skills and 1. n8n expression syntax.

czlonkowski/n8n-skills · 2,609 tokens

activepieces AGENTS.md

AGENTS.md instructions for activepieces/activepieces, covering activepieces, architecture (non-obvious rules), coding conventions, query error handling and key utilities (@activepieces/shared).

activepieces/activepieces · 4,681 tokens

activepieces CLAUDE.md

Claude Code instructions for activepieces/activepieces, covering activepieces, architecture (non-obvious rules), coding conventions, query error handling and key utilities (@activepieces/shared).

activepieces/activepieces · 4,681 tokens

sofagent GEMINI.md

Instructions for KongFangXun/sofagent, covering gemini.md · sofagent gemini cli 适配（薄挂载）, 会话开始时按序加载（四层加载链）, 审计强制（平台无关） and 连接 mcp server.

KongFangXun/sofagent · 464 tokens

obsidian-local-llm-hub AGENTS.md

Instructions for takeshy/obsidian-local-llm-hub, covering repository instructions and version bumps.

takeshy/obsidian-local-llm-hub · 74 tokens

sofagent AGENTS.md

Instructions for KongFangXun/sofagent, covering agents.md · sofagent codex 适配（薄挂载）, 会话开始时按序加载（四层加载链）, modelinstructionsfile（可选）, /.codex/config.toml and 审计强制（平台无关）.

KongFangXun/sofagent · 562 tokens