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/classify-red)<a href="https://agentmods.dev/commands/coleam00/archon/classify-red"><img src="https://agentmods.dev/badge/commands/coleam00/archon/classify-red/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/classify-red"><img src="https://agentmods.dev/badge/commands/coleam00/archon/classify-red.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 | $0.00576 |
| Opus 5.5 | $0.00000 | $0.00230 |
| Sonnet 5.5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
classify-red 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 yesterday.
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 — 18 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Classify a red gate
The project's gate ran and at least one check failed. $ARTIFACTS_DIR/validation.md is the record: every check that ran, its group, its exit status, each failing check's output tail, and the path of each check's full output log. Decide why the failed checks failed, judging every one the record names. You fix nothing and change nothing in the checkout; a re-run you make is evidence, never a way to turn the gate green.
Declare
red_cause— why the gate is red; when several checks failed, the cause that most needs action (introducedoverinheritedoverenvironment):introduced— the change under validation caused the failure.inherited— the same check was already failing at the base this branch came from.environment— the machine caused it, not any code: a database or port a parallel process holds, a missing credential, a network fault, a process killed for memory, or a test that failed in a file the change does not touch, passes when re-run alone on this same tree, and shares nothing the change alters (a mock, a fixture, global or shared test state).
summary— a few sentences: every failing check by name, what failed in each, and the evidence for each cause. A fixer reads this first.
Evidence
Classifying red never makes it green. But inherited and environment let delivery continue, so neither is the comfortable answer: declaring one commits you to evidence. Name the exact failing check and the concrete reason the change under validation cannot have caused it — the same failure on the exact base revision, or a resource another process demonstrably holds. Disjoint changed paths alone do not prove independence; a check can read a path another change moves. $ARTIFACTS_DIR/implementation.md may already record the same red; corroborate it against the recorded output rather than repeating it. Without that evidence the cause is introduced.
To show a failure is inherited, reproduce the narrowest failing piece — the single failing test or file, not the whole gate — at the base revision, in a separate temporary worktree that you remove afterwards. Never check out another revision in the run's own checkout. A failure that passes at the base is not yet introduced: re-run the same narrowest piece on this tree too. When it fails here, it is introduced; when it passes here as well, in a file the change does not touch, and the change alters nothing that test shares with the rest of the run (a mock, a fixture, global or shared test state), the gate's run was disturbed and the cause is environment, with both runs as the evidence.
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.
- yesterday Changed 14dcf02df39f
- 20d ago First seen · 18 lines · 0 tokens per session scan A 9b716c437eef
classify-red is a command published in the GitHub repository coleam00/Archon (23,690 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 576 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 2026-09-26.
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.
hatch3r-bug-plan
Diagnose a complex incident -- reproduce the symptom, rank root-cause hypotheses, design the fix path, and emit regression coverage items as a board-ready investigation.
hatch3r-bug-pipeline
Run a known-cause bug fix through a 3-phase test-first pipeline -- reproduce + root-cause, regression-test + fix together, then root-cause-depth review -- with full sub-agent delegation.
apex-quick
Quick Flow for bounded fixes - the full APEX route with Brainstorm skipped and Plan compressed to one task; Analyze trio, delegated execution, eLicit, Verify, challenger and full sniper always run.
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.