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/dsifry/metaswarm/handle-pr-commentsgit clone --depth 1 https://github.com/dsifry/metaswarmWrote 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/dsifry/metaswarm/handle-pr-comments)<a href="https://agentmods.dev/commands/dsifry/metaswarm/handle-pr-comments"><img src="https://agentmods.dev/badge/commands/dsifry/metaswarm/handle-pr-comments.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 | $0.00000 | $0.04999 |
| Opus 5 | $0.00000 | $0.02499 |
| Sonnet 5 | $0.00000 | $0.01000 |
| Haiku 4.5 | $0.00000 | $0.00500 |
Grade A, and why
handle-pr-comments 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 4d 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 — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/handle-pr-comments
Handle review comments on pull requests with appropriate responses and resolutions.
Usage
/handle-pr-comments <pr-number>
Overview
This command helps systematically address PR review comments from automated tools (like CodeRabbit) and human reviewers. It ensures consistent, professional responses that acknowledge the AI assistance.
CRITICAL: Complete PR Lifecycle Protocol
A PR is NOT complete until ALL of the following are true:
- All CI checks pass
- EVERY code review comment has been addressed (including trivial/nitpicks)
- EVERY comment thread has received an individual response
- All threads are marked as resolved (after reviewer approval)
- Any work > 1 day has a GitHub issue created
- No pending reviewer comments awaiting response
- ALL tests pass, there are no pre-existing issues or flaky tests - these are excuses. Fix the underlying issues, don't disable tests.
- No new reviews after last commit with actionable items (Section 1d)
Mandatory Comment Handling Rules
| Comment Type | Action | DO NOT Skip |
|---|---|---|
| Critical/Major | Fix immediately | Never |
| High/Medium | Fix before merge | Never |
| Minor | Fix | Never |
| Trivial/Nitpick | FIX THESE TOO | These matter! |
| Out-of-scope | INVESTIGATE THOROUGHLY | Often the BEST insights! |
| Human comments | Always address | Never |
Work Sizing Decision
For EACH comment:
- < 1 day of work -> Implement the fix in this PR
- > 1 day of work OR architectural change -> Create a new GitHub issue, link it in your response
Iteration Loop
REPEAT until (all_threads_resolved AND no_new_comments AND no_new_reviews_after_commit):
1. Fetch ALL inline comments (including trivial, out-of-scope)
1b. CHECK REVIEW BODIES for "Outside diff range" comments (Section 1c)
- These are NOT threads - they're in the review body text
- Commonly missed because they don't appear as threads!
2. Check for NEW REVIEWS after last commit (Section 1d)
3. For each comment: fix OR create issue OR respond with disagreement
4. Run validation: lint, typecheck, and tests
5. Commit and push
6. Respond to EVERY thread individually
6b. For "Outside diff range" comments: leave a general PR comment acknowledging
7. CRITICAL: WAIT FOR CI/CD, then RE-CHECK for NEW comments/reviews
- Monitor CI/CD pipeline: `gh pr checks $PR_NUMBER --watch`
- Wait until ALL checks complete (not just pass - complete)
- Automated reviewers (CodeRabbit) post comments during/after their check
- Check BOTH inline threads AND review bodies for new feedback
- Check for NEW REVIEWS with "Actionable comments posted: X" (X > 0)
8. If new comments OR new reviews exist -> GO TO STEP 1
9. If no new comments/reviews AND all checks complete -> verify all threads resolved, then complete
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.
- 4d ago First seen · 532 lines · 0 tokens per session scan A 697abb031c35
handle-pr-comments is a command published in the GitHub repository dsifry/metaswarm (407 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,999 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.