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/update-pr-body)<a href="https://agentmods.dev/commands/coleam00/archon/update-pr-body"><img src="https://agentmods.dev/badge/commands/coleam00/archon/update-pr-body/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/update-pr-body"><img src="https://agentmods.dev/badge/commands/coleam00/archon/update-pr-body.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 | $0.00904 |
| Opus 5.5 | $0.00000 | $0.00362 |
| Sonnet 5.5 | $0.00000 | $0.00181 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
update-pr-body 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update the pull request description
Bring the pull request's description in line with the final change. It was written when the draft opened; the base merge and correction rounds since then may have falsified claims in it, and a validation may have passed red it has to disclose. Your product is an accurate description, nothing else.
The pull request: $INPUTS.pr. Its URL names the repository (host and
<owner>/<repo>) and the number every command below uses. Read and write it
through the source this run selected, $INPUTS.source:
forge: the Archon CLI, whose argv is the JSON string array in$ARCHON_CLI_COMMAND, run as<argv...> forge <op> --json …, with<ref>={"repo":{"host":…,"path":…},"number":…}. Read withpr.viewand--data '{"selector":{"kind":"number","ref":<ref>}}'; write withpr.edit-bodyand--data-file, so the description never reaches a command line. A failed operation is the answer: report it, and never repeat it throughgh.gh: the GitHub CLI, every command naming--repo <host>/<owner>/<repo>.
- Read the live description and base (
pr.view, orgh pr view <number> --repo <host>/<owner>/<repo> --json body,baseRefName): a person may have edited it since, and their edits stay. Then read the full final diff: fetch the base from the remote whose URL is the pull request's repository (git remote -v; it need not be namedorigin) and diff<that remote>/<base>...HEAD. - Check every concrete claim in the description against the diff: named functions and guards, described mechanics, file lists, "unchanged" claims. Change only what the diff falsifies. Keep the structure, the tone and every claim that is still true. Do not rewrite from scratch, add sections other than step 4's, or narrate the correction history.
- When
$ARTIFACTS_DIR/implementation.mdrecords a failing check the implementer judgedinheritedorenvironment, the description must say so near the top: the check and why it is not this change's. Keep an existing disclosure that is still true. - Link the issue the description references by the latest review's contract
coverage. What it left open, as a JSON list (empty text when no review judged
coverage):
$INPUTS.contract_left. On an empty list ([]), and only then, the reference becomesCloses #N, replacing aRefs #N. Anything else gets a non-closing reference (Refs #N) in place of any closing keyword (Closes,Fixes,Resolvesand their variants), and a short "Left open" section listing each item, or saying no review judged coverage. An item left open as an operator check names the check the operator runs. Keep at most one "Left open" section, current, and remove it on an empty list. Change no other reference, and add none when the description links no issue. - When something changed, apply the complete description. On
forge, write the request{"ref":<ref>,"body":<description>}to$ARTIFACTS_DIR/pr-body-final.jsonand pass it with--data-file. Ongh, write the description to$ARTIFACTS_DIR/pr-body-final.mdand apply it withgh pr edit <number> --repo <host>/<owner>/<repo> --body-file "$ARTIFACTS_DIR/pr-body-final.md". When nothing changed, edit nothing.
Never modify files in the checkout, commit, push, change the pull request's draft state, or touch the review comment.
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 · +12 lines 47fe50c85e19
- yesterday Changed · +1 lines 3609069db777
- 2d ago First seen · 47 lines · 0 tokens per session scan A eb7850fb4d0f
update-pr-body 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 904 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 2026-10-15.
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.