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/jvm/pi-mono/claude-mdgit clone --depth 1 https://github.com/jvm/pi-monoWrote 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/jvm/pi-mono/claude-md)<a href="https://agentmods.dev/instructions/jvm/pi-mono/claude-md"><img src="https://agentmods.dev/badge/instructions/jvm/pi-mono/claude-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 | $0.00974 | $0.00974 |
| Opus 5 | $0.00487 | $0.00487 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
pi-mono CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Root-level commands (npm install, check, test, pack:dry-run, validate) and the git/PR workflow are in AGENTS.md — follow that.
Target a single workspace:
npm run check --workspace packages/pi-goal
npm test --workspace packages/pi-goal
npm run pack:dry-run --workspace packages/pi-web-kit
Run a single test file (from within the package directory or using tsx):
node --import tsx --test packages/pi-goal/tests/core.test.mjs
Local Pi testing without installing the package:
pi -e /path/to/pi-mono/packages/<package-name> --print "list your tools"
Architecture
This is an npm workspaces monorepo of Pi packages — extensions for @earendil-works/pi-coding-agent, a coding agent similar to Claude Code. Pi loads TypeScript source files directly at runtime via its built-in extension loader; there is no build step and no dist/ directory in any package.
Package layout
Every package follows the same structure:
packages/<name>/
index.ts # thin re-export: export { default } from "./extensions/index.js"
extensions/index.ts # Pi extension wiring: registers tools, commands, event handlers
src/ # business logic, kept separate from Pi API wiring
src/install-telemetry.ts # telemetry implementation (every publishable package)
tests/ # node:test .test.mjs files (packages that have tests)
Extension API pattern
Extensions default-export a function that receives a pi: ExtensionAPI instance:
export default function myExtension(pi: ExtensionAPI) {
pi.registerTool({ name, parameters, execute, ... });
pi.registerCommand("cmd", { handler });
pi.on("session_start", async () => { ... });
pi.on("before_agent_start", async (event) => ({ systemPrompt: ... }));
}
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 · 83 lines · 974 tokens per session scan A a5dc451b0204
pi-mono CLAUDE.md is an instructions file published in the GitHub repository jvm/pi-mono (21 stars, last pushed 5d ago), licensed MIT. It adds 974 tokens to every session, about $0.0049 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).