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/agentconfig/agentconfig.org/agents-mdgit clone --depth 1 https://github.com/agentconfig/agentconfig.orgWhat 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 | $0.02368 | $0.02368 |
| Opus 5 | $0.01184 | $0.01184 |
| Sonnet 5 | $0.00474 | $0.00474 |
| Haiku 4.5 | $0.00237 | $0.00237 |
Grade A, and why
agentconfig.org 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for agentconfig.org
This file is the authoritative source for AI agent instructions in this repository.
GitHub Copilot and other agents with AGENTS.md support read it directly. Claude Code loads the same instructions through the @AGENTS.md import in CLAUDE.md.
Project Overview
A multi-page reference and tutorial site explaining the configuration files and patterns developers use to customize GitHub Copilot, Claude Code, Cursor, and OpenAI Codex.
Target Audience
Developers who want to:
- Understand what AI primitive files exist (CLAUDE.md, copilot-instructions.md, etc.)
- Know where to place these files in their projects
- Learn which primitives to use for different tasks
Site Structure
The site presents the same source-backed model in several ways:
- Homepage reference - A practical starting example, 13 primitive cards, an interactive file tree, a four-provider comparison, and the scope model
- Progressive tutorials - Skills, agent definitions, lifecycle hooks, and MCP guides that begin with a small working example before concepts and advanced cases
- Provider profiles - Per-provider implementation, support, location, and primary-source documentation for every tracked primitive
- Machine-readable docs -
llms.txt,llms-full.txt, and page-specific Markdown generated from the same typed content
Tech Stack
- Runtime: Bun (not npm)
- Build: Vite
- Framework: Preact 10+ with functional components and hooks
- Styling: Tailwind CSS 4 + shadcn/ui
- Language: TypeScript (strict mode)
- Testing: Playwright for E2E tests
- Linting: ESLint with strict config
- Hosting: GitHub Pages
- Theme: Light/dark mode support
Commands
All commands run from the site/ directory:
bun install # Install dependencies
bun run dev # Start development server (http://localhost:5173)
bun run build # Production build
bun run preview # Preview production build
bun run lint # Run ESLint
bun run typecheck # TypeScript type checking
bun run test # Run Playwright E2E tests
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.
- yesterday First seen · 246 lines · 2,368 tokens per session scan A 9dac599b4473
agentconfig.org AGENTS.md is an instructions file published in the GitHub repository agentconfig/agentconfig.org (7 stars, last pushed 4d ago), licensed ISC. It adds 2,368 tokens to every session, about $0.0118 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.
Other instructions, from other repositories
rosetta mcp-tool-descriptions.instructions.md
Tool descriptions should teach agents how to navigate the surface: workflow arrows, empty-result hints, boundaries, and result-budget cues.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
build-applications-w-copilot-agent-mode octofit_tracker_react_frontend.instructions.md
Instructions for skills/build-applications-w-copilot-agent-mode, covering octofit tracker react presentation tier guidelines and images.
agent-skills AGENTS.md
AGENTS.md instructions for tech-leads-club/agent-skills, covering agents.md, workflow orchestration, 1. plan mode default, 2. subagent strategy and 3. verification before done.
kesha-voice-kit AGENTS.md
Instructions for drakulavich/kesha-voice-kit: Project rules, build commands, release process, and lessons learned live in CLAUDE.md — single source of truth for every coding agent (Claude Code, Cursor, Aider, Codex, etc.). When CLAUDE.md and any other doc disagree, CLAUDE.md wins.
agent-skills CLAUDE.md
Claude Code instructions for tech-leads-club/agent-skills, a project described as: The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.