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/answer)<a href="https://agentmods.dev/commands/coleam00/archon/answer"><img src="https://agentmods.dev/badge/commands/coleam00/archon/answer/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/answer"><img src="https://agentmods.dev/badge/commands/coleam00/archon/answer.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 | $0.01237 |
| Opus 5.5 | $0.00000 | $0.00495 |
| Sonnet 5.5 | $0.00000 | $0.00247 |
| Haiku 4.5 | $0.00000 | $0.00124 |
Grade A, and why
answer 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer How a Build Round Ended
A build round is one archon-ship run on the item. Read how it ended and decide what the queue does next: the item is done, the queue continues it with another round, or a maintainer must decide. The next node performs what you declare and reads it back: it pushes commits the round left unpushed, records your decision, and raises your attention item. You write nothing to the tracker, the repository or the state store yourself, and the checkout must be exactly as you found it when you finish.
The item: $INPUTS.url. Its issue, title and body, is in $ARTIFACTS_DIR/build/issue.md; read the body from there, because it is the text this decision is about. Dated "Current scope" sections are part of the contract and override what they rule on.
The round
- This round's ending, as
archon-ship's report declared it:$INPUTS.ending. Its artifacts are in$ARTIFACTS_DIR:triage.md, thenplan.mdorinvestigation.mdwhen they exist,implementation.md, andreview/report.md. - In a replay the ending above is null, and the round is
$INPUTS.recorded: its report fields and its ownartifactsdirectory. Judge it as the round that just ended, from what was true when it ended. - The earlier rounds, oldest first, each with its own
artifactsdirectory:$INPUTS.rounds. - The item's work item:
$INPUTS.record. Underfacts.buildis every decision the queue made on it, with any maintainer's answer. Null means no queue has recorded it.
Read the SDLC policy files this decision names, at .archon/sdlc/policy/, falling back to the pack's defaults. This decision names build.md and rulings.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. Read the project's steering documents, direction, engineering.md or architecture.md, only when a stop's question turns on what they rule.
Decide
Read the report's reason and summary, then the artifact that explains it: the plan's open questions, the review report's findings, the implementer's dispositions. Read what a finding or a question says; never decide from the reason code alone.
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 · 42 lines · 0 tokens per session scan A cb002dee78a9
answer 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 1,237 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.
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-board-fill
Create epics and issues/work items from todo.md, reorganize the board with dependency analysis, readiness assessment, and implementation ordering. Supports GitHub, Azure DevOps, and GitLab.