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/revisit)<a href="https://agentmods.dev/commands/coleam00/archon/revisit"><img src="https://agentmods.dev/badge/commands/coleam00/archon/revisit/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/revisit"><img src="https://agentmods.dev/badge/commands/coleam00/archon/revisit.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 | $0.00428 |
| Opus 5.5 | $0.00000 | $0.00171 |
| Sonnet 5.5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
revisit 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.
What it actually says
Revisit Blocked Items
Intake recorded each item below as blocked: something had to happen first. Work lands in parallel, so a blocker can be resolved, superseded or made irrelevant while its issue is still open, and an item can stay blocked long after it could move. Judge, for each item, whether it still looks blocked now. You don't re-triage anything yourself: the next node asks intake to re-triage the items you name, and intake decides whether each is ready. You write nothing to the tracker, the repository or the state store, and the checkout must be exactly as you found it.
The items: $INPUTS.blocked, issues in $INPUTS.repo_host/$INPUTS.repo_path. Each has its issue number and intake's summary of its triage, which names what it waits on.
Judge each item
- Read the issue, its recent comments and what it waits on, with the tracker's CLI: the linked issues or pull requests, or the decision it names.
- Check the current state of each blocker: closed, merged, superseded by other work, or still open and still needed. For a code prerequisite, check the default branch:
git fetchthe remote, then read the log and the files the blocker would have changed. An open blocker whose outcome already landed some other way does not block. - Decide:
- re-triage it when the reason intake recorded no longer holds, or probably no longer holds and a fresh triage would settle it. Intake's triage is cheap next to an item that waits for nothing.
- leave it when it still waits on something real: an open prerequisite whose outcome has not landed, or a person's decision nobody has made.
An item blocked on a maintainer's decision stays blocked until the issue or its comments record that decision.
Declare retriage: one entry per item to re-triage, with its number and a reason a maintainer can check in one line, naming the blocker and its state. An empty list sends nothing.
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 First seen · 18 lines · 0 tokens per session scan A 104113b45e20
revisit is a command published in the GitHub repository coleam00/Archon (23,735 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 428 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 2026-10-20.
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.
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-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.
next
Suggest the most likely next workflow action based on current context.