Borrowing it
Nothing to install: this file belongs to pi0/skillman. 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/pi0/skillman/main/AGENTS.mdgit clone --depth 1 https://github.com/pi0/skillmanWrote 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/pi0/skillman/agents-md)<a href="https://agentmods.dev/instructions/pi0/skillman/agents-md"><img src="https://agentmods.dev/badge/instructions/pi0/skillman/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/pi0/skillman/agents-md"><img src="https://agentmods.dev/badge/instructions/pi0/skillman/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 | $0.01378 | $0.01378 |
| Opus 5.5 | $0.00551 | $0.00551 |
| Sonnet 5.5 | $0.00276 | $0.00276 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
skillman 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 2mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
skillman is a CLI wrapper to manage project skills and lock them in skills.json. It provides a declarative way to install skills per project, similar to how package managers work with package.json.
Architecture
src/
├── cli.ts # CLI entry point with parseArgs
├── config.ts # skills.json config management
├── skills.ts # Skills CLI execution
└── utils/
├── colors.ts # ANSI color codes for terminal output
└── gitignore.ts # .gitignore file management
test/index.test.ts # Tests using vitest
Config (src/config.ts)
findSkillsConfig(cwd?)— Findsskills.jsonby traversing up from cwdreadSkillsConfig(options?)— Reads and validatesskills.json(options:{ cwd?, createIfNotExists? })updateSkillsConfig(updater, options?)— Generic update with callback (options:{ cwd?, createIfNotExists? }, defaultscreateIfNotExists: true)addSkill(source, skills?, options?)— Adds a skill source (options:{ cwd?, createIfNotExists? }, defaultscreateIfNotExists: true)- Auto-injects
$schemafield during validation if missing
Skills CLI (src/skills.ts)
findSkillsBinary(options?)— Finds localskillsbinary in node_modules/.bin (options:{ cache? }, cached by default)installSkills(options?)— Spawnsskills addfor each source with progress logging; options:{ cwd?, agents?, global?, yes? }installSkillSource(entry, options)— Installs a single skill source; options:{ cwd?, agents?, global?, yes?, prefix? }
CLI Entry (src/cli.ts)
main(argv?)— CLI entry point using Node.jsparseArgsparseSource(input)— Parses source input into{ source, skills }; supports:- Colon/comma format:
owner/repo:skill1,skill2orowner/repo:skill1:skill2 - skills.sh URLs:
https://skills.sh/owner/repo/skill-name
- Colon/comma format:
Utils (src/utils/)
colors.ts — ANSI escape codes for terminal styling:
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.
- 2mo ago First seen · 148 lines · 1,378 tokens per session scan A 12c7a6e2786f
skillman AGENTS.md is an instructions file published in the GitHub repository pi0/skillman (190 stars, last pushed 6mo ago), licensed MIT. It adds 1,378 tokens to every session, about $0.0055 per session on Opus 5.5. 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.
skillman AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skillman AGENTS.mdpi0/skillman | Instructions file | 190 | 6mo ago | MIT | A | 1,378 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |