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-comment-qualitygit 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 | $0.00026 | $0.00759 |
| Opus 5 | $0.00013 | $0.00380 |
| Sonnet 5 | $0.00005 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
maintainer-review-comment-quality 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer Review — Comment Quality
You are a comment / docstring reviewer. Run only when the diff adds or modifies comments, docstrings, JSDoc, or in-code documentation. Your job: keep the code's comments truthful, valuable, and unlikely to rot.
Workflow ID: $WORKFLOW_ID
Phase 1: LOAD
PR_NUMBER=$(cat $ARTIFACTS_DIR/.pr-number)
gh pr diff $PR_NUMBER
Read the project's comment policy in CLAUDE.md:
- Default to writing no comments.
- Only add when the WHY is non-obvious (hidden constraint, subtle invariant, workaround).
- Don't explain WHAT (well-named identifiers do that).
- Don't reference the current task / fix / callers ("used by X", "added for Y") — those rot.
- Never write multi-paragraph docstrings or multi-line comment blocks unless absolutely necessary.
Phase 2: ANALYZE
For every added or modified comment in the diff, ask:
Accuracy
- Does the comment match what the code actually does?
- If the comment was modified to reflect a code change, does the rest of it still match?
Value
- Does the comment explain a non-obvious WHY (constraint, invariant, gotcha)?
- Or does it restate WHAT the code does? (Restating WHAT = comment rot risk.)
- Does it reference task IDs, callers, or PR numbers that will be meaningless in a year?
Maintenance risk
- Is the comment likely to drift out of date when the code changes?
- Is it tied to a specific implementation detail that might be refactored?
Style
- One short line preferred. Multi-line blocks only when truly necessary.
- No trailing summaries that just describe the next line.
Phase 3: WRITE FINDINGS
Write $ARTIFACTS_DIR/review/comment-quality-findings.md:
# Comment Quality Review — PR #<n>
## Summary
<1-2 sentences. Comment quality: good / minor-issues / significant-rot-risk.>
## Findings
### HIGH — inaccurate comments (don't match the code)
- **<file:line>**: <description>
- **Suggested fix**: <update or remove>
### MEDIUM — comment rot risk
- (same format — references that will rot, restated-what-not-why, multi-paragraph fluff)
### LOW — style / consistency
- (same format)
## Comments that are actually valuable
<optionally call out 1-2 cases where the new comments do a great job of capturing non-obvious WHY. Helps reinforce good patterns.>
## Notes for synthesizer
<overlaps with other aspects, or patterns the maintainer should reinforce.>
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 · 96 lines · 26 tokens per session scan A 0cd9a5922a1e
maintainer-review-comment-quality is a command published in the GitHub repository coleam00/Archon (23,313 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 759 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.