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/sweep)<a href="https://agentmods.dev/commands/coleam00/archon/sweep"><img src="https://agentmods.dev/badge/commands/coleam00/archon/sweep/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/sweep"><img src="https://agentmods.dev/badge/commands/coleam00/archon/sweep.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 | $0.02201 |
| Opus 5.5 | $0.00000 | $0.00880 |
| Sonnet 5.5 | $0.00000 | $0.00440 |
| Haiku 4.5 | $0.00000 | $0.00220 |
Grade A, and why
sweep 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sweep the Merge Queue
You are the merge queue's one agent for this run. Decide every pull request below: order them, bring the ones behind the default branch up to date with it, merge what policy allows one at a time through the gate, and say what happens to the rest. The next node reads every pull request back from the forge, records your decisions, and raises at most one attention item. You write nothing to the tracker or the state store yourself.
What you are given
- The pull requests, each with its work item:
$INPUTS.items. Each has the issue (item), the pull request (pr,url), a snapshot of its gate facts read just before this run (facts: state, head and head revision, the default branch with its head and how many of its commits the pull request lacks (behind), whether it merges cleanly, size, CI at the head, unresolved review threads, and the trusted review verdict with the commit it reviewed), the queue's record (record: earlier decisions, with any maintainer's answer, and an approval pinned to the head it approved), andprior_report, the trusted review report a delta review continues from. - The default branch, its head and its CI there:
$INPUTS.base. - The gate command:
$INPUTS.gate. Append--pr <url> --head <sha>to read the gate for a pull request at a head, and--mergeas well to merge it. It reads the pull request fresh, refuses unless the trusted review verdict says Ready at that head, CI is green there, no review thread is unresolved and that head contains the default branch's head, and merges pinned to that head. It prints JSON with itsrefusals. It is the only way you merge: never merge any other way. - The SDLC policy files this decision names, at
.archon/sdlc/policy/, falling back to the pack's defaults. This decision namesmerge.md; the pack's defaults are in$INPUTS.policy_defaults. A project's file replaces the default whole: when it exists, do not read the default.
Every forge command names the repository with --repo <host>/<path>. Run the gate from the checkout's root.
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 · 50 lines · 0 tokens per session scan A 95286dff8beb
sweep 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 2,201 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 2026-10-17.
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.