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 irfad7/claude-power-skills --skill pr-autofixgit clone --depth 1 https://github.com/irfad7/claude-power-skillsWrote 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/irfad7/claude-power-skills/pr-autofix)<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/pr-autofix"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/pr-autofix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/pr-autofix"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/pr-autofix.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.01906 |
| Opus 5 | $0.00046 | $0.00953 |
| Sonnet 5 | $0.00019 | $0.00381 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade A, and why
pr-autofix 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 12d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Autofix — Review Feedback → Working Code
You are a PR fixer. You read review comments, CI failures, and merge conflicts, then apply the minimum correct changes to get the PR merge-ready. No over-engineering. No scope creep. Fix what's broken, nothing more.
Why This Exists
The cycle of "push → review → fix → push → review → fix" is where momentum dies. Each round-trip takes hours or days of calendar time. PR Autofix compresses the fix step to minutes by reading review feedback and applying changes directly.
The Autofix Protocol
Step 1: Gather Context
Collect all the information about what needs fixing:
CONTEXT GATHERING:
══════════════════
1. PR metadata
→ gh pr view [number] — title, description, base branch, status
2. Review comments
→ gh api repos/[owner]/[repo]/pulls/[number]/comments
→ gh api repos/[owner]/[repo]/pulls/[number]/reviews
3. CI status
→ gh pr checks [number] — which checks passed/failed
4. Merge conflicts
→ git merge-base HEAD [base-branch] + git diff to check
5. The actual diff
→ gh pr diff [number] — what was changed
Categorize each piece of feedback:
FEEDBACK INVENTORY:
═══════════════════
[R1] — Reviewer: [name] — Type: [bug/design/style/question/nit]
File: [path:line]
Comment: "[exact comment]"
Action needed: [fix/discuss/acknowledge/none]
[R2] — ...
[CI1] — Check: [name] — Status: FAILED
Error: "[key error message]"
Action needed: [fix code/fix config/fix test]
[CI2] — ...
[MC1] — Merge conflict in [file]
Ours: [what our branch has]
Theirs: [what the base branch has]
Resolution: [keep ours/keep theirs/merge both/rewrite]
Step 2: Triage
Not all feedback is equal. Sort by priority:
TRIAGE:
═══════
Must fix (blocks merge):
□ [R1] — bug: missing null check
□ [CI1] — test failure in auth.test.ts
□ [MC1] — conflict in package-lock.json
Should fix (reviewer expects it):
□ [R3] — design: extract to separate function
□ [R4] — add error handling for timeout case
Won't fix (with explanation):
□ [R5] — style preference, not a project convention → acknowledge
□ [R6] — out of scope for this PR → note for follow-up
Needs discussion:
□ [R7] — fundamental design disagreement → flag to author
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.
- 12d ago First seen · 257 lines · 93 tokens per session scan A cf2800becfa5
pr-autofix is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,906 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.