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 skills add eugeniughelbur/agents-md --skill agents-mdgit clone --depth 1 https://github.com/eugeniughelbur/agents-mdWrote 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/skills/eugeniughelbur/agents-md/agents-md)<a href="https://agentmods.dev/skills/eugeniughelbur/agents-md/agents-md"><img src="https://agentmods.dev/badge/skills/eugeniughelbur/agents-md/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/skills/eugeniughelbur/agents-md/agents-md"><img src="https://agentmods.dev/badge/skills/eugeniughelbur/agents-md/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 | $0.00174 | $0.01837 |
| Opus 5 | $0.00087 | $0.00919 |
| Sonnet 5 | $0.00035 | $0.00367 |
| Haiku 4.5 | $0.00017 | $0.00184 |
Grade A, and why
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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agents-md
Generate and maintain a high-quality AGENTS.md for the current repository, then wire
the other agent tools to it. AGENTS.md is the converging cross-tool standard (OpenAI 2025,
now Linux Foundation / Agentic AI Foundation governance, 60k+ repos). One AGENTS.md is read
by most coding agents; CLAUDE.md and others are pointed at it via symlink.
This skill is safe to re-run. It only rewrites the regions it generated (marked with HTML comments) and never overwrites content a human wrote. That guarantee is the whole point.
When invoked, do this in order
1. Locate the repo and take stock
- Repo root:
git rev-parse --show-toplevel(fall back to the current directory). - Detect existing agent files:
AGENTS.md,CLAUDE.md,.cursor/rules/or.cursorrules,.github/copilot-instructions.md,.windsurfrules,GEMINI.md. - If
AGENTS.mdexists, check whether it contains this skill's markers (<!-- agents-md:begin ... -->). That decides the write mode in step 4.
2. Gather facts from the repo (never guess — read)
Read, don't assume. Pull real values from these sources:
| Need | Read |
|---|---|
| Language / framework | package.json, pyproject.toml / requirements.txt, go.mod, Cargo.toml, Gemfile, composer.json, pom.xml, *.csproj |
| Build / test / run / lint commands | package.json scripts, Makefile, Taskfile, justfile, tox.ini, pyproject [tool.*] |
| Project / file structure | top-level dirs + the main source dir (src/, app/, lib/, cmd/) |
| Git workflow | default branch (git symbolic-ref refs/remotes/origin/HEAD), last ~15 commits for message/branch conventions, CONTRIBUTING.md |
| Deploy / runtime | Dockerfile, .github/workflows/, railway.json/railway.toml, vercel.json, fly.toml, Procfile |
| Env / secrets | .env.example (NEVER read or copy real .env values) |
| Overview | README.md (summarize, do not duplicate it wholesale) |
For a monorepo, generate one root AGENTS.md and offer per-package AGENTS.md in each workspace (agents read the nearest one).
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.
- 9d ago First seen · 113 lines · 174 tokens per session scan A 4b5366ab812d
agents-md is a skill published in the GitHub repository eugeniughelbur/agents-md (9 stars, last pushed 2mo ago), licensed MIT. It adds 174 tokens to every session and 1,837 once invoked, about $0.0009 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 skills, from other repositories
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
toolport
Use when the user asks for any external action or data: email, payments, deployments, databases, repos, issues, files, web search, messaging, or any connected service. Toolport is the front door to every MCP server on this machine; search it before concluding a capability is unavailable.
skill-push
Create and push reusable skills to SkillNote from Codex when repeated instructions are detected or the user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection, and publishing.
skillnote-doctor
A diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file validity, and installed skill health. Use when your setup seems broken, skills aren't loading, or you want to audit your agent's configuration.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
complete-skill
Rate a SkillNote skill after using it in Codex. Called after applying a skill to record a 1-5 rating and outcome.