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/heyhuynhgiabuu/openpi/agents-mdgit clone --depth 1 https://github.com/heyhuynhgiabuu/openpiWrote 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/heyhuynhgiabuu/openpi/agents-md)<a href="https://agentmods.dev/instructions/heyhuynhgiabuu/openpi/agents-md"><img src="https://agentmods.dev/badge/instructions/heyhuynhgiabuu/openpi/agents-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 | $0.05814 | $0.05814 |
| Opus 5 | $0.02907 | $0.02907 |
| Sonnet 5 | $0.01163 | $0.01163 |
| Haiku 4.5 | $0.00581 | $0.00581 |
Grade B, and why
openpi AGENTS.md scanned grade B with 2 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
TypeScript modules with **full system permissions**. They execute arbitrary code, call any Node API, and make network requests. Pi's extension API: `ExtensionAPI` with `registerTool`, `registerCommand`, `registerShortcut Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Git authority: read (status, diff), stage (add specific files), commit, push, revert, checkout — all owned exclusively by Electron main via `simple-git` or child_process. Never via Pi tools, Pi SDK, or renderer code. How it starts
The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPi Project Rules
Purpose: Project-level operating rules for building OpenPi: a desktop workbench for the Pi coding agent (@earendil-works/pi-coding-agent v0.84.1+).
Audience: human developers and AI coding agents.
Related surfaces:
ROADMAP.md— philosophy, phases, non-goals (read before proposing product scope).STATUS.md— current feature status, beta surface, known constraints.~/.pi/agent/APPEND_SYSTEM.md— global system prompt supplement (workflow routing, tool selection, persona). Loaded every turn. Project-local.pi/APPEND_SYSTEM.mdis intentionally absent so the global takes effect.node_modules/@earendil-works/pi-coding-agent/— installed SDK; see## Pi Documentation Sourcesbelow for the canonical doc table.
Product Direction
OpenPi is a local-first desktop workbench for Pi (@earendil-works/pi-coding-agent, upstream earendil-works/pi). It hosts the MIT agent in Electron main and renders session tree, tools, Git, editor, and terminal — not a second agent runtime, not VS Code/Warp, not a Codex/Kun parity product.
For agents implementing features: Pi is intentionally minimal (small prompt, four core tools, YOLO by default). Pi ships without built-in plan mode, todos, MCP, permission gates, or sub-agents — those belong in user extensions or documented Pi examples. OpenPi adds inspectability (UI, tokens, Git/diff) and optional desktop policy (protected paths, high-risk confirms in main). Treat the human as the quality gate — prefer review surfaces and Phase 7 P0 work (diff review before apply, test evidence) over velocity features (auto-commit stacks, agent armies, new builtins). Do not propose Kun runtimes, SDD wizards, senpi-style permission/todo forks in main, or influencer “extension stack” installers unless the user explicitly asks.
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 · 423 lines · 5,814 tokens per session scan B 42a98f4d0ca2
openpi AGENTS.md is an instructions file published in the GitHub repository heyhuynhgiabuu/openpi (214 stars, last pushed today), licensed MIT. It adds 5,814 tokens to every session, about $0.0291 per session on Opus 5. A static security scan graded it B with 2 findings (unrestricted tool access, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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.
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).