ai AGENTS.md

Repository instructions for a collection of reusable OpenCode and Pi Coding Agent files, including agent profiles, prompts, skills, and Nix configuration. Nix is a tool for defining reproducible system and development setups.

In plain words
What is it for?
Use them when editing the repository’s agent assets, Nix modules, or Pi TypeScript extensions, then run the specified validation commands.
Why use it?
They set rules for keeping changes focused and private, and list the checks needed to catch invalid Nix or TypeScript changes.

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/adampoit/ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/adampoit/ai

Made for: Codex, OpenCode.

Per session 222 This file is loaded in full into every session.
When invoked 222 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 $0.00222 $0.00222
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash 71c4a6906d95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai 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 yesterday.

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 · 30 lines

What it actually says

Repository Guide

This repository contains reusable OpenCode and Pi Coding Agent assets:

  • global-instructions.md for shared rules
  • agents/ for agent profiles
  • prompts/ for command prompts
  • skills/ for skill docs and helper scripts
  • nix/opencode.nix for the Home Manager OpenCode configuration module
  • nix/pi-coding-agent.nix for Pi Coding Agent Home Manager customizations

Working Principles

  • Keep changes small and focused.
  • Match existing style and conventions in nearby files.
  • Prefer self-documenting code over explanatory comments.
  • Do not add secrets, tokens, private URLs, or personal data.

Validation

For Nix module edits, validate flake/module syntax:

  • nix flake show --no-write-lock-file
  • nix-instantiate --parse ./nix/opencode.nix
  • nix-instantiate --parse ./nix/pi-coding-agent.nix

For Pi TypeScript extension edits, run:

  • npm run typecheck
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. yesterday First seen · 30 lines · 222 tokens per session scan A 71c4a6906d95

Subscribe to this mod's changes

ai AGENTS.md is an instructions file published in the GitHub repository adampoit/ai (2 stars, last pushed 7d ago), licensed MIT. It adds 222 tokens to every session, about $0.0011 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 2026-08-31.