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/.github/prompts/create-rules.prompt.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/commands/coleam00/archon/create-rules)<a href="https://agentmods.dev/commands/coleam00/archon/create-rules"><img src="https://agentmods.dev/badge/commands/coleam00/archon/create-rules.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 5.1 | $0.00014 | $0.00898 |
| Opus 5 | $0.00007 | $0.00449 |
| Sonnet 5 | $0.00003 | $0.00180 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
create-rules 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 today.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Global Rules
Generate a .github/copilot-instructions.md file by analyzing the codebase and extracting patterns.
Objective
Create project-specific custom instructions that give Copilot context about:
- What this project is
- Technologies used
- How the code is organized
- Patterns and conventions to follow
- How to build, test, and validate
Phase 1: DISCOVER
Identify Project Type
First, determine what kind of project this is:
| Type | Indicators |
|---|---|
| Web App (Full-stack) | Separate client/server dirs, API routes |
| Web App (Frontend) | React/Vue/Svelte, no server code |
| API/Backend | Express/Fastify/etc, no frontend |
| Library/Package | main/exports in package.json, publishable |
| CLI Tool | bin in package.json, command-line interface |
| Monorepo | Multiple packages, workspaces config |
| Script/Automation | Standalone scripts, task-focused |
Analyze Configuration
Look at root configuration files:
package.json → dependencies, scripts, type
tsconfig.json → TypeScript settings
vite.config.* → Build tool
*.config.js/ts → Various tool configs
Map Directory Structure
Explore the codebase to understand organization:
- Where does source code live?
- Where are tests?
- Any shared code?
- Configuration locations?
Phase 2: ANALYZE
Extract Tech Stack
From package.json and config files, identify:
- Runtime/Language (Node, Bun, Deno, browser)
- Framework(s)
- Database (if any)
- Testing tools
- Build tools
- Linting/formatting
Identify Patterns
Study existing code for:
- Naming: How are files, functions, classes named?
- Structure: How is code organized within files?
- Errors: How are errors created and handled?
- Types: How are types/interfaces defined?
- Tests: How are tests structured?
Find Key Files
Identify files that are important to understand:
- Entry points
- Configuration
- Core business logic
- Shared utilities
- Type definitions
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.
- today First seen · 167 lines · 14 tokens per session scan A c7ac0c2f80ea
create-rules is a command published in the GitHub repository coleam00/Archon (23,398 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 898 once invoked, about $0.0001 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 2026-09-08.
Other commands, from other repositories
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
triage
Classify/label newly opened GitHub issues missing labels.
release
Release all packages at specified version.
cleanup
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
doc
System prompt for /doc slash command.
explain
System prompt for /explain slash command.