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/review-scope)<a href="https://agentmods.dev/commands/coleam00/archon/review-scope"><img src="https://agentmods.dev/badge/commands/coleam00/archon/review-scope/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/review-scope"><img src="https://agentmods.dev/badge/commands/coleam00/archon/review-scope.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 | $0.02509 |
| Opus 5.5 | $0.00000 | $0.01004 |
| Sonnet 5.5 | $0.00000 | $0.00502 |
| Haiku 4.5 | $0.00000 | $0.00251 |
Grade A, and why
review-scope 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Scope
Establish exactly what this review round examines, and write it down for the reviewer or reviewers that follow. You do not judge anything; you make the target precise.
Inputs
Requested scope (may be empty):
$INPUTS.scope
Previous round's report (path; empty means this is the first round, full review):
$INPUTS.prior_report
Commit under review: read the checkout's HEAD with git rev-parse HEAD. Every diff you record ends at that full SHA, never a branch name or a revision read from a pull-request record. The mode node validates continuation ancestry after this node accepts the PR head; publication refuses when the checkout or the pull request's remote head differs from the reviewed commit.
Previous round's reviewed commit (only after the head matches): read reviewed-head beside the supplied prior report. This is the cursor this round's delta starts from, not a SHA inferred from the report's prose.
Accepted work order (may be empty for a standalone review):
$INPUTS.work_order
Part assignment (empty when this run delivers the whole contract; mode validates its schema before lenses run):
$INPUTS.part
The run's trigger message, which may narrow or override the above:
$ARGUMENTS
Resolve the target
- When the requested scope is a recorded pull request — delivery passes its verified record as JSON, carrying
repo,number,headandbase— review exactly that pull request. The record names the pull request and its base, so read nothing from a forge to establish them. It does not name the commit: itshead_revisionwas captured when the pull request opened and is stale after any later push, so ignore it. The review object is the diff of the commit under review against that base. Fetch the base first, from the remote whose URL is the record'srepo(git remote -v; it need not be namedorigin), and diff against the fetched ref (git diff <that remote>/<base>...<commit under review>): a local<base>branch can lag the forge's base during a long run, and a stale base reviews a diff the pull request does not have. Do not resolve a PR from the current branch, and do not accept a different target. - A PR number, URL, or branch → resolve it with
gh pr view(title, body, base, head, state, files) andgh pr diff. The PR's head must be the commit under review; when it is not, stop and say so rather than reviewing either one. In PR mode the review object is the PR's diff, exactly — uncommitted or untracked local state is out of scope and must not appear in the scope file. - Empty scope → first check whether the current branch has an open PR (
gh pr view); if it does, that PR is the target (PR mode, as above). Otherwise the working diff: uncommitted changes plus commits ahead of the merge-base with the default/base branch (git merge-base,git diff,git log). The head is the commit under review.
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 986bc9c34afb
- 4d ago Changed · -3 lines bf1d871b61b4
- 5d ago Changed · +7 lines d1d17e1e216e
- 6d ago Changed · -4 lines 41df2ed983d4
- 15d ago Changed ce40afe8ec2e
- 16d ago Changed · +10 lines 2fc49561fa29
- 18d ago Changed dc11756d24a6
- 26d ago Changed · +6 lines 27f637b79417
- 27d ago Changed · +3 lines 6067b9ea5d46
- 1mo ago First seen · 61 lines · 0 tokens per session scan A aefc7d68345c
review-scope is a command published in the GitHub repository coleam00/Archon (23,735 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,509 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
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
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-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.