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/.claude/commands/create-command.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-command)<a href="https://agentmods.dev/commands/coleam00/archon/create-command"><img src="https://agentmods.dev/badge/commands/coleam00/archon/create-command/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/commands/coleam00/archon/create-command"><img src="https://agentmods.dev/badge/commands/coleam00/archon/create-command.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 | $0.00010 | $0.02071 |
| Opus 5.5 | $0.00004 | $0.00828 |
| Sonnet 5.5 | $0.00002 | $0.00414 |
| Haiku 4.5 | $0.00001 | $0.00207 |
Grade A, and why
create-command 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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Claude Code creating a command for Claude Code. The agent executing the generated command has your exact capabilities:
- Task tool with subagents (Explore, Plan, code-reviewer, etc.)
- Read, Write, Edit, Glob, Grep tools
- Bash execution
- WebSearch and WebFetch
- Extended thinking for complex analysis
Meta Principle: The command you create will be executed by an agent identical to you. Write instructions you would want to receive.
Phase 1: ANALYZE - Understand the Command Request
PARSE the input:
- Command name: Extract from first argument
- Purpose: Extract from remaining arguments
- Command type: Determine category
CLASSIFY command type:
| Type | Characteristics | Examples |
|---|---|---|
| WORKFLOW | Multi-phase, produces artifacts, needs subagents | plan-feature, rca |
| ACTION | Single operation, immediate result | commit, create-pr |
| ANALYSIS | Investigates codebase, produces report | rca, review |
| UTILITY | Helper task, quick execution | validate, check-ignores |
DETERMINE requirements:
- Does it need arguments? → Add
argument-hint - Does it need tool restrictions? → Add
allowed-tools - Does it produce files? → Define output path
- Does it need codebase exploration? → Plan for Explore agent
- Does it need external research? → Plan for WebSearch
PHASE_1_CHECKPOINT:
- Command name is kebab-case
- Purpose is clear and specific
- Command type identified
- Requirements mapped
Phase 2: EXPLORE - Study Existing Patterns
Use Task tool with subagent_type="Explore" to analyze:
Explore .claude/commands/ to find patterns for creating a new command.
DISCOVER:
1. YAML frontmatter patterns - description, argument-hint, allowed-tools
2. XML tag usage - which tags are used and when
3. Phase structure - how commands break down work
4. Checkpoint patterns - how self-validation is done
5. Output format patterns - how results are reported
6. Dynamic context usage - !`commands` and @file references
Focus on commands similar to the one being created.
Return actual snippets showing the patterns.
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.
- 17d ago Changed 4b9cadef5671
- 1mo ago First seen · 305 lines · 10 tokens per session scan A e4e24676ecdb
create-command is a command published in the GitHub repository coleam00/Archon (23,752 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 2,071 once invoked, about $0.0000 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 2026-08-30.
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.
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
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.
hatch3r-workflow
Guided development lifecycle with 4 phases (Analyze, Plan, Implement, Review) and scale-adaptive Quick Mode for small tasks; --plan-file executes an approved plan document without re-deriving it.