Borrowing it
Nothing to install: this file belongs to narumiruna/pi-extensions. 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/narumiruna/pi-extensions/main/AGENTS.mdgit clone --depth 1 https://github.com/narumiruna/pi-extensionsWrote 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/narumiruna/pi-extensions/agents-md)<a href="https://agentmods.dev/instructions/narumiruna/pi-extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/narumiruna/pi-extensions/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/narumiruna/pi-extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/narumiruna/pi-extensions/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 | $0.03053 | $0.03053 |
| Opus 5.5 | $0.01221 | $0.01221 |
| Sonnet 5.5 | $0.00611 | $0.00611 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
pi-extensions 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 3d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Documentation
- Lead with the most important information and use concise, accurate prose without repetition.
- Use concise paragraphs for human-facing narrative and lists only when separate items are easier to scan.
- Keep
AGENTS.mdinstructions as one-sentence, enforceable bullet points. - Follow
docs/readme-conventions.mdfor active package READMEs, including its required sections, warnings, scope rules, and verification checklist. - Keep package versions out of long-lived guidance and derive them from manifests, lockfiles, or workflows.
Code style
- Follow KISS and YAGNI, add dependencies only for current needs, and use Pi core functions when they already provide the required behavior.
- Use NodeNext modules, ES2024, strict TypeScript, and no emit for root TypeScript.
- Upgrade outdated dependencies instead of removing or downgrading valid code to hide their type errors.
- Split source files over 1,000 lines by clear responsibility, but do not mechanically split generated, vendored, migration, snapshot, or mainly declarative files.
Commands and tooling
- Run commands from the repository root unless their documentation says otherwise.
- Use
npm installto install dependencies,npm run formatto apply Biome formatting, andnpm run typecheckto typecheck every workspace. - Run
npm runbefore adding or documenting a root workflow command. - Keep root npm scripts as canonical entrypoints only for workflows users run from the root, and move complex implementations under
scripts/. - Keep pre-commit hook logic in
scripts/pre-commit.sh, invoke it directly from.husky/pre-commit, and do not add a duplicate root npm script. - Do not run root checks concurrently with a
pi-tui-kitbuild or check because both clearpackages/pi-tui-kit/dist. - Rebuild
pi-tui-kitbefore consumer tests because consumers resolve its built output. - After raising a consumer's Kit floor, run root
npm install, verify the resolution withnpm ls @narumitw/pi-tui-kit, and then typecheck. - Keep imported Pi packages in root
devDependenciesso tests emitted undernode_modules/.cacheresolve the intended versions. - Prefer Pi AI root exports, and use a variable-specifier dynamic import only when a required subpath has no root export because official Pi can misresolve static
@earendil-works/pi-ai/api/*imports. - Treat Pi's user and project managed npm roots as separate install scopes because deduplication is guaranteed only within one root.
- Never use
npm audit fix --force; if it changes Pi dependencies, restore every workspace manifest and the lockfile before applying targeted patched upgrades or overrides.
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.
- 3d ago Changed · +1 lines · +32 tokens per session 02be7bec712e
- 11d ago Changed aa0472877c90
- 1mo ago Changed · -1 lines · -16 tokens per session 6547603e2b17
- 1mo ago Changed · -37 lines · -441 tokens per session 25b166b36fd5
- 2mo ago Changed · +2 lines · +113 tokens per session c4e8c6fd92c2
- 2mo ago Changed · +23 tokens per session fe69c8a8b10e
- 2mo ago First seen · 178 lines · 3,342 tokens per session scan A e33ebf8f6ae7
pi-extensions AGENTS.md is an instructions file published in the GitHub repository narumiruna/pi-extensions (757 stars, last pushed yesterday), licensed MIT. It adds 3,053 tokens to every session, about $0.0122 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-extensions AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pi-extensions AGENTS.mdnarumiruna/pi-extensions | Instructions file | 757 | yesterday | MIT | A | 3,053 | 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 |