Archon is a workflow engine for AI coding agents that turns development processes into YAML-defined sequences with phases, validation gates, and artifacts. Developers use it to run repeatable processes such as planning, implementation, testing, code review, and pull-request creation across projects. The catalogue entries provide commands, agents, skills, hooks, instructions, and settings for working with Archon.
Borrowing it
Nothing to install: this file belongs to coleam00/Archon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/coleam00/Archon/dev/AGENTS.mdgit clone --depth 1 https://github.com/coleam00/ArchonWrote 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/coleam00/archon/agents-md)<a href="https://agentmods.dev/instructions/coleam00/archon/agents-md"><img src="https://agentmods.dev/badge/instructions/coleam00/archon/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/coleam00/archon/agents-md"><img src="https://agentmods.dev/badge/instructions/coleam00/archon/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03687 | $0.03687 |
| Opus 5.5 | $0.01475 | $0.01475 |
| Sonnet 5.5 | $0.00737 | $0.00737 |
| Haiku 4.5 | $0.00369 | $0.00369 |
Grade A, and why
Archon 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Archon
Archon is a self-hostable, governed agentic automation engine. It runs workflows that mix deterministic steps, AI agents, human gates, and audit trails. Coding automation is its most mature surface, but the engine is intended for general business operations too.
This file is the canonical project guidance for coding agents. Keep it short, durable, and about judgment. Put changing product direction in .archon/direction.md, workflow-language design in .archon/workflow-language-constitution.md, aspirational engineering craft and review values in .archon/engineering.md, user documentation in the docs site, and machine-checkable rules in code, types, tests, lint, or CI.
Read before changing code
- Treat the source, its call sites, and its tests as the current evidence. The request defines the goal and constraints, but a prompt may describe old code.
- Read every relevant consumer before changing a producer, contract, path, identifier, schema, or generated artifact.
- Reproduce bugs when practical. If reproduction is impossible, establish another concrete causal chain before editing.
- Do not trust a passing test by itself. Check that it exercises the behavior it claims to protect.
- A question is read-only. Explain first; change code only when the user asks for a change.
- Do not stop at editing. Finish the requested change and verify the outcome.
- If the implementation keeps getting more complicated, stop and reconsider the model. Solve the underlying problem.
Product boundaries
- Archon is a governed automation engine, not a replacement for the coding agents it orchestrates.
- One install serves one operator or client. Client isolation belongs at the deployment layer. Multiple users within one install are supported and are not multi-tenancy.
- Keep the conversation layer platform-agnostic. Platform adapters translate transport details; core behavior should not depend on Slack, Telegram, GitHub, Discord, CLI, or Web UI semantics.
- Keep the core self-hostable. Do not make a proprietary hosted service a runtime dependency.
- Keep the core small and flexible. Agentic engineering changes too quickly for one monolith to encode every useful workflow or integration; give users stable seams to assemble and extend the rest.
- Treat bundled workflows as reference implementations, not a frozen compatibility surface.
- A git worktree separates checkouts; it is not an execution or security sandbox.
- Consult
.archon/direction.mdbefore making product-scope or architecture-direction decisions.
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 Changed · -8 tokens per session 65652ada1bce
- 2d ago Changed · +34 tokens per session 459a464807b2
- 5d ago Changed · +2 lines · +137 tokens per session 9269ea17cefc
- 6d ago Changed · -2 tokens per session 1d5bcc1f2124
- 7d ago Changed · +1 lines · +27 tokens per session 679eff9a5863
- 9d ago Changed · +2 tokens per session b9f57598625a
- 20d ago Changed · -2 tokens per session 1938aad5f6b8
- 1mo ago Changed · +70 tokens per session ad9f69a1cd4f
- 1mo ago First seen · 195 lines · 3,429 tokens per session scan A c05a8c09d758
Archon AGENTS.md is an instructions file published in the GitHub repository coleam00/Archon (23,752 stars, last pushed today), licensed MIT. It adds 3,687 tokens to every session, about $0.0147 per session on Opus 5.5. 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 2026-09-03.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.