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/tgyd-helige/pi/agents-mdgit clone --depth 1 https://github.com/TGYD-helige/piWrote 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/tgyd-helige/pi/agents-md)<a href="https://agentmods.dev/instructions/tgyd-helige/pi/agents-md"><img src="https://agentmods.dev/badge/instructions/tgyd-helige/pi/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 | $0.04423 | $0.04423 |
| Opus 5 | $0.02211 | $0.02211 |
| Sonnet 5 | $0.00885 | $0.00885 |
| Haiku 4.5 | $0.00442 | $0.00442 |
Grade A, and why
pi 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 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi Extensions Monorepo — Agent Guidelines
Project Overview
This monorepo contains Pi extensions (packages/pi-*), a shared library (packages/shared), and integration tests (tests/). Most packages are Pi extensions — TypeScript modules that hook into the Pi agent runtime.
Required Agent Skills
Two external skill sets are mandatory when developing in this repo. Install them for your harness before starting work; if your harness cannot install skills, follow the rules inlined below.
ponytail — minimal-code discipline
Every code change follows ponytail's ladder — stop at the first rung that holds:
1. Does this need to exist? → no: skip it (YAGNI)
2. Already in this codebase? → reuse it, don't rewrite (check sibling packages and packages/shared first)
3. Stdlib does it? → use it
4. Native platform feature? → use it
5. Installed dependency? → use it — no new deps for one-call problems
6. One line? → one line
7. Only then: the minimum that works
The ladder runs after understanding the problem, never instead of it: read the code the change touches and trace the real flow before picking a rung. Lazy about the solution, never about reading — and never about trust-boundary validation, data-loss handling, security, or accessibility.
Install:
- Claude Code:
/plugin marketplace add DietrichGebert/ponytail, then/plugin install ponytail@ponytail(two separate prompts) - Codex:
codex plugin marketplace add DietrichGebert/ponytail && codex plugin add ponytail@ponytail, then trust its two lifecycle hooks under/hooks
mattpocock/skills — engineering workflow skills
Use this skill set for process work in this repo:
triage— processing new issues/PRs (labels: thetype/*+P0–P3set managed by.github/workflows/labeler.yml)to-spec/to-tickets— before non-trivial implementationstdd— behavior changes in packages with existing coverage (see Unit Test Convention)diagnosing-bugs— no fix without a reproduced root causeresearch,code-review,resolving-merge-conflicts— as named
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 · 404 lines · 4,423 tokens per session scan A a654f322e44b
pi AGENTS.md is an instructions file published in the GitHub repository TGYD-helige/pi (59 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,423 tokens to every session, about $0.0221 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
telos AGENTS.md
AGENTS.md instructions for HarperZ9/telos, covering telos agent instructions, scope, developer contract and verification.
browser-use AGENTS.md
AGENTS.md instructions for browser-use/browser-use, covering agents.md version 2, development rules, quickstart, 1. installing browser-use and on windows use .venv\scripts\activate.
browser-use CLAUDE.md
Claude Code instructions for browser-use/browser-use, covering claude.md, high-level architecture, core components, event-driven browser management and cdp integration.
browser-control AGENTS.md
Instructions for keon/browser-control: Use this project as a tiny browser pipe, not an agent framework.
SmolVM AGENTS.md
AGENTS.md instructions for CelestoAI/SmolVM, covering smolvm context, 🚀 project overview, 🧪 development, key commands and release checklist.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.