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/classify-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/classify-review-scope)<a href="https://agentmods.dev/commands/coleam00/archon/classify-review-scope"><img src="https://agentmods.dev/badge/commands/coleam00/archon/classify-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 | $0.00000 | $0.00443 |
| Opus 5 | $0.00000 | $0.00221 |
| Sonnet 5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
classify-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 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
Choose this delivery's review scope
Decide whether the pull request that was just opened warrants either optional review lens. Code, seams, simplify, and tests run on every full review; only errors and docs are yours to select. No one watches this run; your structured verdict is the only thing downstream nodes read.
Ground the decision in the PR itself, not the work item: read the current
branch's pull request description and its complete diff (the gh CLI is
available; the PR for this branch was opened by an earlier node). Judge what is
actually in the change. Do not modify any file.
What each optional lens hunts
- errors — failure paths made silent: new catch/fallback/retry/default-value code, error translation, recovery behavior, anything where a failure could become indistinguishable from success.
- docs — shipped documentation changed by the diff.
Calibration
Cost is not the constraint; wasted attention is. A small, mechanical, likely-correct diff — a version bump, a one-line fix, a rename, a test-only tweak — often earns neither optional lens. A substantial or risky diff earns each lens whose failure class plausibly lives in it: when the diff genuinely contains new failure paths, choose errors; when it changes shipped documentation, choose docs. Do not economize on real risk, and do not manufacture scope for its absence.
The test for each lens is the same: does this diff contain material that its failure class could plausibly live in? Decide from what you saw, not from the workflow's name or the issue's topic.
Declare (every turn)
One boolean per optional lens, plus a reasons object with one sentence per
lens citing what in the diff decided it — for a false, what the diff lacks;
for a true, what it contains. An operator's explicit errors setting overrides
that verdict downstream; auto adopts it.
errors,docs— booleansreasons—{errors, docs}, one sentence each
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 66f2e0128183
classify-review-scope is a command published in the GitHub repository coleam00/Archon (23,366 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 443 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.