Borrowing it
Nothing to install: this file belongs to romiluz13/pi-agent-skills. 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/romiluz13/pi-agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/romiluz13/pi-agent-skillsWrote 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/romiluz13/pi-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/romiluz13/pi-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/romiluz13/pi-agent-skills/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/romiluz13/pi-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/romiluz13/pi-agent-skills/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 | $0.00584 | $0.00584 |
| Opus 5.5 | $0.00234 | $0.00234 |
| Sonnet 5.5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
pi-agent-skills 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 — 19 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guidance (pi-skill repo)
This repository combines vendor pi-mono/ and **pi-skills/** (code-grounded Agent Skills). Treat them as separate concerns unless a task touches both.
Before you edit pi-skills/
- Read
**docs/working-with-pi-mono.md**for clone layout, pin semantics, and links to upstream docs. For assertions → machine needles, read**docs/needle-rules.md. For the full skill-creator loop (eval workspace, viewer,run_loop), follow**pi-skills/docs/skill-creator-workspace.md. Contributing:**CONTRIBUTING.md**. - Ground skill content in real paths under
pi-mono/that exist in the working tree. - Before claiming done:
cd pi-skills && npm run verify-skills(or**npm run ci** to match GitHub Actions: regrade baselines then all gates). If you changedevals/all-evals.json, alsonpm run sync-evals, update matching**evals/examples/<id>.eval_metadata.json**, and keep**evals/graded-examples/<id>/assertions.json**aligned with**extract-grade-assertions**(**verify-graded-needles**).**verify-eval-artifacts**requires catalog, metadata, and graded dirs in lockstep.**verify-packs-in-sync**and**verify-all-evals-shape**lock pack manifests and eval JSON shape (including**skill_evals**order vs**pi.skills**).**verify-graded-needles-in-response**requires baseline**with_skill/response.md**to contain every graded needle.**verify-trigger-evals**enforces each**pi.skills**entry has a valid**trigger-evals/*.json**. - Do not add
**TODO**, placeholders, or uncited APIs. Extend**scripts/api-allowlist.json**only when a new symbol is intentionally part of the contract.
Before you edit pi-mono/
Follow **pi-mono/AGENTS.md** and **pi-mono/CONTRIBUTING.md**. Run Pi’s **npm run check** and **./test.sh** from pi-mono/. If upstream paths cited in skills move or rename, update the corresponding **pi-skills/pi-*/SKILL.md** and evals.
Corpus bump
When pi-mono HEAD should become the new truth: cd pi-skills && npm run bump-corpus, then verify + sync as above.
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 · 19 lines · 584 tokens per session scan A fe98a9d8a989
pi-agent-skills AGENTS.md is an instructions file published in the GitHub repository romiluz13/pi-agent-skills (20 stars, last pushed 6mo ago), licensed MIT. It adds 584 tokens to every session, about $0.0023 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.
pi-agent-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pi-agent-skills AGENTS.mdromiluz13/pi-agent-skills | Instructions file | 20 | 6mo ago | MIT | A | 584 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |