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.
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.
git 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/pr)<a href="https://agentmods.dev/commands/coleam00/archon/pr"><img src="https://agentmods.dev/badge/commands/coleam00/archon/pr/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/pr"><img src="https://agentmods.dev/badge/commands/coleam00/archon/pr.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 | $0.00000 | $0.01382 |
| Opus 5.5 | $0.00000 | $0.00553 |
| Sonnet 5.5 | $0.00000 | $0.00276 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
pr 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare the Pull Request
Prepare a clear, reviewer-friendly pull request for the committed work on the current branch. You never modify source files, and you never push, create, edit, or comment on the pull request yourself: your one write is the body file below. The node that follows pushes the branch and performs the one public write, through whichever forge source the run selected. You do not merge the base: a conflict with it is found by CI and resolved by the implementer.
Draft mode: $INPUTS.draft — true opens as a draft; anything else, ready for review. A pull request that already exists keeps the draft state its author gave it.
Context from the run that may narrow this (often empty):
$ARGUMENTS
1. Establish the target
Record HEAD_BRANCH=$(git branch --show-current) before doing anything else; an empty value is a hard failure, as is a HEAD with no commits. Resolve the repository the pull request opens against from the checkout's remotes (git remote -v): the repository this work is proposed to, which in a fork setup is the upstream the fork was made from, not the fork. Whatever the remotes are named, declare its canonical forge identity as host plus path (owner/repo), with transport syntax, credentials, and a trailing .git stripped; GitHub's HTTPS, [email protected]:..., and ssh://[email protected]/... forms all declare host github.com. Remotes that do not identify one repository are a hard failure. Never persist or print a credential-bearing raw remote.
Determine the base branch from evidence, in order: the repository's documented development flow (steering files, CONTRIBUTING); branch ancestry against likely integration branches (dev, development, the remote default); an existing pull request for this exact branch. Never assume main. Use the same resolved base for every diff.
When this run continues an existing pull request — the caller resolved it ($INPUTS.pull_request; empty or null when it named none), the run's context names its number, or the run was launched onto it — record that number and the qualified head repository and head branch it belongs to. HEAD must descend from that pull request's current head revision; if it does not, stop and report rather than prepare a replacement. If the head lives in a fork and the author did not allow maintainer edits, this run cannot publish to it: stop and report.
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 Changed 78e8ba5c961f
- yesterday Changed · +2 lines ee5231398a35
- 2d ago Changed · -12 lines 878028e043f1
- 23d ago Changed · +14 lines f6ee3ad85da1
- 1mo ago Changed · +2 lines 841a5c403f75
- 1mo ago Changed · +2 lines 7b3c3f605154
- 1mo ago First seen · 41 lines · 0 tokens per session scan A 847be9f2229d
pr is a command published in the GitHub repository coleam00/Archon (23,701 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,382 tokens. 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.
release
Release all packages at specified version.
triage
Classify/label newly opened GitHub issues missing labels.
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-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.