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/ci)<a href="https://agentmods.dev/commands/coleam00/archon/ci"><img src="https://agentmods.dev/badge/commands/coleam00/archon/ci/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/ci"><img src="https://agentmods.dev/badge/commands/coleam00/archon/ci.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 | $0.02688 |
| Opus 5.5 | $0.00000 | $0.01075 |
| Sonnet 5.5 | $0.00000 | $0.00538 |
| Haiku 4.5 | $0.00000 | $0.00269 |
Grade A, and why
ci 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wait for CI and judge it
The pull request's review has passed. CI is the project's full validation: the implementer checked only what it changed. Mark the pull request ready, wait for its CI to conclude on the current head, judge what the result means, and act on it. No one watches this run; your structured answer and $ARTIFACTS_DIR/ci.md are all the next node reads.
The pull request is the one this round published: $INPUTS.pr. That record names its repository (repo.host, repo.path), number, head branch and base; act on exactly that pull request, never one found from the checkout's remotes or branch. Every forge read and write goes through the source this run selected, $INPUTS.source:
forge: the Archon CLI, whose argv is the JSON string array in$ARCHON_CLI_COMMAND, run as<argv...> forge <op> --json --data '<request>'. With<ref>={"repo":{"host":…,"path":…},"number":…}from the record:pr.viewtakes{"selector":{"kind":"number","ref":<ref>}};pr.ready,pr.draftandchecks.statetake{"ref":<ref>};checks.reruntakes{"ref":<ref>,"revision":…,"units":[…]}. Achecks.stateanswer carries therevisionit evaluated, each unit's conclusion, and asummarywhosecountsgive the number of units in each state and whosestate(none,pending,green,red,gatedorunknown) is the worst unit's: one red unit makes itredwhile others are stillpending. A failed operation is the answer: report it, and never repeat it throughgh.gh: the GitHub CLI, every command naming the repository with--repo <host>/<path>: in a clone of a fork, gh otherwise resolves the upstream parent.
Mark it ready, then wait
If the pull request is merged, declare green: there is nothing to mark. If it is closed without a merge, declare other and say so. Otherwise confirm the pull request's head is this checkout's HEAD: CI is never judged against a stale head. When the pull request's head is an ancestor of HEAD (a commit was made here but not pushed), push HEAD to the pull request's head branch by name (git push <remote> HEAD:refs/heads/<branch>; never force, never let git pick an upstream) and read the remote head back. If the push fails, or the two heads have diverged, declare other with the evidence. When the pull request's head carries commits this checkout's HEAD does not, someone pushed after this round's review and no review covered them: do not mark it ready, put it back to draft if it is ready, and declare other naming those commits. A continuation delivery reviews them before the pull request counts as ready again.
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 Changed · +3 lines c798c617541d
- yesterday Changed · +2 lines fa3f4bd09e71
- 2d ago First seen · 51 lines · 0 tokens per session scan A 8aeeb6eefc41
ci 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 2,688 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 2026-10-15.
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.
watch-ci
Monitor CI/CD pipeline and automatically fix failures. Watches GitHub Actions runs and applies fixes when tests fail.