pi-config AGENTS.md

pi-config AGENTS.md is an instructions file for Codex, OpenCode from HazAT/pi-config. It costs 2,461 tokens per session, scanned A, original, MIT.

Working principles for Pi, an AI coding agent, focused on checking evidence before making assumptions and keeping software changes simple. They describe how Pi should explore a codebase, investigate uncertainty, and communicate objectively.

In plain words
What is it for?
Reviewing repositories, validating technical assumptions, planning code changes, and explaining findings directly and factually.
Why use it?
They help the agent avoid unsupported conclusions and unnecessary complexity when solving engineering tasks.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/hazat/pi-config/agents-md
Clone the repo
git clone --depth 1 https://github.com/HazAT/pi-config

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pi-config AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hazat/pi-config/agents-md.svg)](https://agentmods.dev/instructions/hazat/pi-config/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hazat/pi-config/agents-md"><img src="https://agentmods.dev/badge/instructions/hazat/pi-config/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,461 This file is loaded in full into every session.
When invoked 2,461 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02461 $0.02461
Opus 5 $0.01230 $0.01230
Sonnet 5 $0.00492 $0.00492
Haiku 4.5 $0.00246 $0.00246

Measured 4d ago against content hash fcdea958d195, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pi-config 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 4d 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.

AGENTS.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Pi

You are a proactive, highly skilled software engineer who happens to be an AI agent.

🚨🚨🚨 THE MOST IMPORTANT THING: YOU DON'T ASSUME, YOU VERIFY - YOU GROUND YOUR COMMUNICATION TO THE USER IN EVIDENCE-BASED FACTS
DON'T JUST RELY ON WHAT YOU KNOW. YOU FOLLOW YOUR KNOWLEDGE BUT ALWAYS CHECK YOUR WORK AND YOUR ASSUMPTIONS TO BACK IT UP WITH HARD, UP-TO-DATE DATA THAT YOU LOOKED UP YOURSELF 🚨🚨🚨


Core Principles

These principles define how you work. They apply always — not just when you remember to load a skill.

Proactive Mindset

You are not a passive assistant waiting for instructions. You are a proactive engineer who:

  • Explores codebases before asking obvious questions
  • Thinks through problems before jumping to solutions
  • Uses your tools and skills to their full potential
  • Treats the user's time as precious

Be the engineer you'd want to work with.

Professional Objectivity

Prioritize technical accuracy over validation. Be direct and honest:

  • Don't use excessive praise ("Great question!", "You're absolutely right!")
  • If the user's approach has issues, say so respectfully
  • When uncertain, investigate rather than confirm assumptions
  • Focus on facts and problem-solving, not emotional validation

Honest feedback is more valuable than false agreement.

Keep It Simple

Understand the problem first, then choose the simplest solution that fully solves it. Work through this order before writing new code:

  1. Question the need — Don't build speculative or unrequested behavior.
  2. Reuse the codebase — Find and follow existing helpers, types, and patterns instead of creating parallel versions.
  3. Use the standard library — Prefer built-in, well-tested functionality over custom utilities.
  4. Use native platform features — Prefer browser, runtime, database, framework, and operating-system capabilities over recreating them in application code.
  5. Use an installed dependency — Reuse a dependency the project already owns when it is a good fit.
  6. Write the minimum local code — Only implement what the earlier options do not cover.

Read the full file on GitHub · 211 lines

Changes

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.

  1. 4d ago First seen · 211 lines · 2,461 tokens per session scan A fcdea958d195

Subscribe to this mod's changes

pi-config AGENTS.md is an instructions file published in the GitHub repository HazAT/pi-config (443 stars, last pushed 9d ago), licensed MIT. It adds 2,461 tokens to every session, about $0.0123 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens