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 skills add tomsej/pi-ext --skill pr-review-commentsgit clone --depth 1 https://github.com/tomsej/pi-extWrote 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/skills/tomsej/pi-ext/pr-review-comments)<a href="https://agentmods.dev/skills/tomsej/pi-ext/pr-review-comments"><img src="https://agentmods.dev/badge/skills/tomsej/pi-ext/pr-review-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 5.1 | $0.00043 | $0.01137 |
| Opus 5 | $0.00022 | $0.00568 |
| Sonnet 5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
pr-review-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 7d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Comments
Triage and address review comments on a pull request: read each comment, decide if valid, fix code, verify tests pass, reply, and resolve threads.
Prerequisites
ghCLI authenticated- Working directory inside the repo (or use
--repo owner/repo)
Workflow
1. Fetch review comments
Get all review comments with context:
gh api repos/{owner}/{repo}/pulls/{pr}/comments \
--jq '.[] | {id, path, line, body, user: .user.login}'
Also check top-level PR comments (non-inline):
gh api repos/{owner}/{repo}/issues/{pr}/comments \
--jq '.[] | {id, body, user: .user.login}'
2. Triage each comment
For each comment, decide:
- Valid & actionable → fix the code
- Valid but won't fix → reply with rationale
- Invalid / misunderstanding → reply with explanation
- Question → answer it
Read the relevant file context before deciding. Don't blindly accept or reject.
3. Fix code
Apply fixes for valid comments. Group related fixes into a single commit. Use conventional commit style:
fix(<scope>): address PR review comments
- <summary of fix 1>
- <summary of fix 2>
Stage, commit, and push.
4. Validate tests pass
After fixing code, always run tests before pushing to make sure the fixes don't break anything:
- Run the project's test command (check project docs /
CLAUDE.md/Makefile/misetasks for the right command). - If tests fail, fix the issue before pushing. A review fix that breaks CI is worse than the original comment.
- If the fix changes test expectations (e.g., updated output values), update the tests too.
- Pay special attention to mock/stub setups — removing or changing mocks can cause unrelated tests to fail when test infrastructure intercepts more than expected (e.g.,
mock_providerintercepting locally-evaluated data sources).
Only push once all tests are green.
5. Reply to comments
Reply to each review comment thread using the in_reply_to field:
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.
- 7d ago First seen · 136 lines · 43 tokens per session scan A 81ced2862716
pr-review-comments is a skill published in the GitHub repository tomsej/pi-ext (70 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 1,137 once invoked, about $0.0002 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.