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/review-scopegit 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.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 5.1 | $0.00000 | $0.01001 |
| Opus 5 | $0.00000 | $0.00500 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 61 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
Accepted work order (may be empty for a standalone review):
$INPUTS.work_order
The run's trigger message, which may narrow or override the above:
$ARGUMENTS
Resolve the target
- When the requested scope is a bare PR number, delivery recorded it — review exactly that PR. Derive the normalized
owner/repofromoriginwithout writing its raw URL into an artifact, and usegh ... --repo <owner/repo>with that number for every GitHub read. Do not resolve a PR from the current branch, and do not accept a different target. The review object is that PR's diff, exactly. - A PR number, URL, or branch → resolve it with
gh pr view(title, body, base, head, state, files) andgh pr diff. Make sure the PR's head is what the local checkout reflects; note the head SHA. 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). Note the current HEAD SHA.
Resolve the accepted contract
- When
work_orderis non-empty, read it in full. It is the accepted contract implementation received. Preserve its required outcome, explicit non-goals, and boundaries as prose; do not parse it with scripts, regexes, or keyword extraction. - When
work_orderis empty and the target is a PR, use the PR body's problem/outcome and explicit scope or non-goals as the standalone review contract. Do not infer a broader promise from the changed files. - When neither supplies an explicit boundary, state that the review is using the requested scope and repository contracts without inventing a non-goal.
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.
- 6d ago First seen · 61 lines · 0 tokens per session scan A aefc7d68345c
review-scope is a command published in the GitHub repository coleam00/Archon (23,374 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,001 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.