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/decide)<a href="https://agentmods.dev/commands/coleam00/archon/decide"><img src="https://agentmods.dev/badge/commands/coleam00/archon/decide/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/decide"><img src="https://agentmods.dev/badge/commands/coleam00/archon/decide.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 | $0.01265 |
| Opus 5.5 | $0.00000 | $0.00506 |
| Sonnet 5.5 | $0.00000 | $0.00253 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
decide 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decide Each Discovery
Finished runs recorded discoveries: defects and gaps they proved outside their own change. Decide what becomes of each one, once. You judge and author; the next node performs exactly the writes you declare and nothing else. 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 repository: $INPUTS.repo_host/$INPUTS.repo_path. The base commit every claim is checked against: $INPUTS.base_sha.
Read first
$ARTIFACTS_DIR/drain/queue.json: the queued runs and their undecided records. Each record has arefof the form<run-id>:<ref>, a title, a claim and its evidence.reviewed: truemeans the run's review certified it;falseis a raw record no review judged. Each run'sartifactsdirectory holds the run's own report,discoveries.mdand anything the evidence cites; open them when a record needs its context.$ARTIFACTS_DIR/drain/discovery-decisions.md: every decision made so far, one section per key, with its outcome, reason, the runs that found it, and any question asked with the maintainer's answer. This is your memory. Search it before deciding anything.- The project's direction document, where it has one: at the root, in a config directory such as
.archon/, or wherever its steering files point. - The SDLC policy files this decision names, at
.archon/sdlc/policy/, falling back to the pack's defaults. This decision namesdiscoveries.md,triage.mdandrulings.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. - The project's
engineering.mdandarchitecture.md, only when a decision depends on what they rule.
Decide every record
For every record in the queue:
- Verify the claim at the base. Read the code the evidence cites with
git show $INPUTS.base_sha:<path>andgit grep <pattern> $INPUTS.base_sha. Never check out, switch, reset or edit anything. A record's file:line evidence was true when its run wrote it; the base may have moved since. Do not run tests or probes: a claim you cannot settle by reading is unverified. - Check memory. A key in
discovery-decisions.mdthat describes the same defect is the same discovery, however differently it is worded. Use its key. - Search the tracker, read-only: open and recently closed issues and pull requests that may already cover it. On GitHub,
gh issue list --repo $INPUTS.repo_host/$INPUTS.repo_path --state all --search "<terms>"andgh pr listwith the same flags. Read an issue and its comments (gh issue view <n> --commentswith the same--repo) before you say it covers a record or that nothing does: the evidence an issue already holds is often in a comment, not its body. - Merge duplicates. Records from different runs, or several records in one run, that describe one defect are one decision: list every one of their refs under it. Related defects that one change would fix may share one filed issue the same way.
- Decide under the policy.
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 · 43 lines · 0 tokens per session scan A 7af85b2aa1d6
decide 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 1,265 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.