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.
npx agentmods add commands/coleam00/archon/sync-pr-bodygit 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/sync-pr-body)<a href="https://agentmods.dev/commands/coleam00/archon/sync-pr-body"><img src="https://agentmods.dev/badge/commands/coleam00/archon/sync-pr-body.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 | $0.00000 | $0.00510 |
| Opus 5 | $0.00000 | $0.00255 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
sync-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 5d 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.
What it actually says
Sync the PR description with the final diff
Bring the pull request description back in line with the code after correction rounds changed it. The description was written when the draft PR opened; corrections since then may have falsified specific claims in it. Your product is an accurate PR body — nothing else.
Read-only on the repository: never modify files, commit, push, change the PR's draft state, or touch the canonical review comment. The PR body is the only thing you may edit.
The target is the run-owned PR, never the current branch's ambient PR mapping:
- Its recorded number is $INPUTS.pr_number.
- Its recorded head branch is $INPUTS.pr_head.
Derive the origin repository, read that exact PR by number, and fail unless its
head and the checked-out branch both equal the recorded head branch. Use the
recorded number as the selector for every gh read or edit.
- Read the current PR body and the full final diff
(
gh pr diff <number> --repo <owner/repo>). - Check every concrete claim in the body against the final diff: named functions and guards, described mechanics, file lists, "unchanged" claims. The Problem section describes the issue and rarely drifts; the Solution and review-guidance sections are where correction rounds falsify claims.
- Edit only what the diff falsifies. Preserve the body's structure, tone, and every claim that is still accurate. Do not rewrite from scratch, do not add sections, and do not narrate the correction history or this sync.
- When nothing is falsified, change nothing.
One exception to "add no sections": if
$ARTIFACTS_DIR/red-causes.jsonrecords a red the body does not already disclose, add that disclosure — cause and its evidence from$ARTIFACTS_DIR/implementation.md. A correction round can go red after the body was written, and a reviewer must not have to discover that from a red badge. - After an edit, read the body back (
gh pr view) and confirm it carries your corrections.
Before finishing, re-read the final body once against the diff: every mechanism it describes must be one the diff actually contains.
Report which claims you corrected and the verified PR URL — or that the body was already accurate and you changed nothing.
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.
- 5d ago First seen · 43 lines · 0 tokens per session scan A dde7d584b68e
sync-pr-body is a command published in the GitHub repository coleam00/Archon (23,374 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 510 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.
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.
hello
Say hello.