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/espennilsen/pi/agents-mdgit clone --depth 1 https://github.com/espennilsen/piWhat 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 | $0.01903 | $0.01903 |
| Opus 5 | $0.00951 | $0.00951 |
| Sonnet 5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
pi 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Personal Pi agent home directory, symlinked to ~/.pi/agent. Contains local extensions, custom skills, prompt templates, and agent profiles. Each extension is a self-contained Node.js package in extensions/ with its own AGENTS.md for detailed context.
Directory Layout
├── agents/ # Agent profile prompt overrides (planner, reviewer, scout, worker)
├── extensions/ # Local extensions (each has own package.json + AGENTS.md)
├── skills/ # Shared skills (changelog-generator, git-project-status, etc.)
├── .pi/
│ ├── skills/ # Project-specific skills (code-review, github, blog-post, etc.)
│ └── prompts/ # Prompt templates (implement, scout-and-plan, implement-and-review)
├── themes/ # Custom TUI themes
├── db/ # Runtime SQLite databases (gitignored)
├── cache/ # Runtime cache (gitignored)
├── sessions/ # Agent session state (gitignored)
└── telemetry/ # Local telemetry data (gitignored)
Extensions
22 local extensions in extensions/. Each has its own AGENTS.md with detailed architecture, entity models, and conventions — read those before modifying an extension.
Key extensions:
- pi-webserver — shared HTTP server with auth; other extensions mount on it
- pi-kysely — shared database registry with table-level RBAC
- pi-myfinance — personal finance (accounts, transactions, vendors, budgets, reports)
- pi-personal-crm — contacts, companies, interactions
- pi-channels — bidirectional messaging (Telegram, webhooks)
- pi-memory — persistent long-term memory and daily logs
- pi-vault — Obsidian vault integration
Extension Development Conventions
Structure
- Default export:
export default function (pi: ExtensionAPI) { ... } - Import types from
@earendil-works/pi-coding-agent(ExtensionAPI,getAgentDir,SettingsManager) - TypeScript with
strict: true, target ES2022, module ESNext,allowImportingTsExtensions - Use
.tsextensions in imports (e.g.import { foo } from "./bar.ts") - Tool parameter schemas use
@sinclair/typebox(Type.Object,Type.String, etc.) - Tool results return
{ content: [{ type: "text", text: "..." }], details: {} }
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.
- 2d ago First seen · 135 lines · 1,903 tokens per session scan A 638cef1a6d7f
pi is an instructions file published in the GitHub repository espennilsen/pi (117 stars, last pushed 9d ago), licensed MIT. It adds 1,903 tokens to every session, about $0.0095 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
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.
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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.