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/xyiqq/skilldoctor/agents-mdgit clone --depth 1 https://github.com/xyiqq/skilldoctorWrote 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/xyiqq/skilldoctor/agents-md)<a href="https://agentmods.dev/instructions/xyiqq/skilldoctor/agents-md"><img src="https://agentmods.dev/badge/instructions/xyiqq/skilldoctor/agents-md.svg" alt="Measured on agentmods" 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 | $0.00406 | $0.00406 |
| Opus 5 | $0.00203 | $0.00203 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
skilldoctor 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 5d 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.
What it actually says
AGENTS.md
Cursor Cloud specific instructions
skilldoctor is a self-contained TypeScript CLI (and GitHub Action) that lints,
audits, and compatibility-checks Agent Skills (SKILL.md). There is no backend,
database, browser UI, or other external service — everything runs locally in the
Node.js process.
Environment
- Requires Node.js >= 18.18 (the VM ships Node 22, which is fine). Uses
npmwithpackage-lock.json; do not switch package managers. - The update script already runs
npm install, so dependencies are present when a session starts. There are no services to launch.
Standard commands (defined in package.json and .github/workflows/ci.yml)
- Typecheck:
npm run typecheck - Tests (Vitest):
npm test(watch:npm run test:watch) - Build (emits to
dist/):npm run build - Full gate (mirrors CI):
npm run ci(typecheck + test + build) - Run from source without building:
npm run dev -- <args>(e.g.npm run dev -- lint examples) - Run the built CLI:
node dist/cli.js <command>(e.g.ci,lint,audit,compat,score,init,rules,explain,fix)
Notes
dist/is committed and is the published artifact (the GitHub Action'saction.ymlpoints atdist/action.js). After changing anything undersrc/, runnpm run buildsodist/stays in sync before committing.- CLI commands exit non-zero when findings meet the
--fail-onthreshold (or when zero skills are found for non-scancommands); this is expected behavior, not an environment failure.
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.
- 5d ago First seen · 31 lines · 406 tokens per session scan A 84a5bc064b72
skilldoctor AGENTS.md is an instructions file published in the GitHub repository xyiqq/skilldoctor (11 stars, last pushed 20d ago), licensed MIT. It adds 406 tokens to every session, about $0.0020 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
marketing-machine CLAUDE.md
Instructions for cagatayuncu/marketing-machine, covering marketing-machine — contributor notes, commands, architecture in ten lines and invariants (violating these is a bug, not a style choice).
humanize AGENTS.md
AGENTS.md instructions for shir-danishyar/humanize: This repository is an Agent Skills-format skill. To use it.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
kleosrules AGENTS.md
AGENTS.md instructions for kleosr/kleosrules, covering agents.md — repository agent handbook, law, pack, skills (on demand) and workflows.