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.
npx agentmods add commands/coleam00/archon/maintainer-standupgit 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/maintainer-standup)<a href="https://agentmods.dev/commands/coleam00/archon/maintainer-standup"><img src="https://agentmods.dev/badge/commands/coleam00/archon/maintainer-standup.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.03418 |
| Opus 5 | $0.00010 | $0.01709 |
| Sonnet 5 | $0.00004 | $0.00684 |
| Haiku 4.5 | $0.00002 | $0.00342 |
Grade A, and why
maintainer-standup 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 6d ago.
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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer Standup Synthesis
You are producing a daily maintainer briefing for the Archon project. The user is the maintainer running this workflow. Your job is to read the gathered facts, cross-reference against the project's direction document and the maintainer's profile, and produce a prioritized brief plus state to persist for tomorrow's run.
Workflow ID: $WORKFLOW_ID
Output format (read this FIRST, follow exactly)
Your response must be exactly two parts in order:
- Brief markdown — starting with the literal line
# Maintainer Standup — YYYY-MM-DDand continuing through the brief. - State JSON block — delimited by
ARCHON_STATE_JSON_BEGINandARCHON_STATE_JSON_END, each on its own line, with valid JSON between them.
Hard rules:
- Start the response with the
#heading. No prose preamble. No "Looking at the data...", no<thinking>, no analysis dump, no "Now I'll synthesize...". - Do NOT wrap the response in a JSON object. Specifically: do NOT output
{"brief_markdown": "...", "next_state": {...}}— that is the OLD contract and is wrong. - Do NOT use markdown code fences around the
ARCHON_STATE_JSON_BEGIN/ARCHON_STATE_JSON_ENDmarkers — the markers must be plain lines. - Nothing after the closing marker. The closing marker is the last line of your response.
Skeleton example (illustrative — your actual brief uses real content):
# Maintainer Standup — 2026-04-29
## Since last run
- ...
## P1 — Do today
- **PR #N** — ...
ARCHON_STATE_JSON_BEGIN
{"last_run_at":"2026-04-29T07:00:00Z","last_dev_sha":"abc123","carry_over":[],"observed_prs":[{"number":1,"title":"x"}],"observed_issues":[],"direction_questions":[]}
ARCHON_STATE_JSON_END
(In your real output the markers and JSON are NOT inside a code fence.)
Phase 1: LOAD INPUTS
You have three sources of upstream context, all already gathered. Each is a JSON string that you should parse.
Git status (origin/dev movement since last run)
$git-status.output
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.
- 6d ago First seen · 244 lines · 19 tokens per session scan A 2b36c22ec948
maintainer-standup is a command published in the GitHub repository coleam00/Archon (23,389 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 3,418 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.
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.
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-refactor-plan
Plan a refactoring or migration effort -- spawn parallel researchers, produce refactoring spec, ADR(s), and phased todo.md entries for board-fill.
csm-workledger
Show the surviving work-ledger entries across sessions.