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-review-reportgit clone --depth 1 https://github.com/coleam00/ArchonWhat 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 | $0.00015 | $0.00475 |
| Opus 5 | $0.00008 | $0.00237 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
maintainer-review-report 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
Maintainer Review — Final Report
You are the final reporter. The workflow has finished the deep review. Your job: produce a one-screen summary that tells the maintainer what just happened and what's pending.
Workflow ID: $WORKFLOW_ID
Phase 1: LOAD ARTIFACTS
PR_NUMBER=$(cat $ARTIFACTS_DIR/.pr-number 2>/dev/null)
ls $ARTIFACTS_DIR/
ls $ARTIFACTS_DIR/review/ 2>/dev/null
$ARTIFACTS_DIR/review/synthesis.md should exist and contain the synthesized verdict + findings.
Phase 2: WRITE THE FINAL REPORT
Write $ARTIFACTS_DIR/final-report.md:
# Maintainer Review — PR #<n> — Final
## Outcome
- Synthesized verdict: <ready-to-merge | minor-fixes-needed | blocking-issues>
- Findings: <N CRITICAL / N HIGH / N MEDIUM / N LOW>
- Aspects run: <list>
- **Draft comment**: $ARTIFACTS_DIR/review/review-comment.md (already posted to PR; copy-paste if you want to edit and re-post)
- **Full synthesis**: $ARTIFACTS_DIR/review/synthesis.md
## Next steps for the maintainer
<2-3 short bullets. e.g.:
- "Open PR #<n> and confirm the posted review reads well."
- "If blocking-issues: wait for contributor reply; check back in N days."
- "If ready-to-merge: merge when CI is green.">
Phase 3: RETURN
Return a single-line outcome:
PR #<n> — verdict=<synthesized verdict>, action=posted-review-comment.
CHECKPOINT
-
$ARTIFACTS_DIR/final-report.mdwritten. - Numbers in the report match
$ARTIFACTS_DIR/review/synthesis.md(don't invent finding counts). - Lists concrete next steps for the maintainer.
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 · 62 lines · 15 tokens per session scan A e6ac8646d4da
maintainer-review-report is a command published in the GitHub repository coleam00/Archon (23,313 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 475 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.
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.
hello
Say hello.