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 slbug/claude-ruby-grape-rails --skill pr-reviewgit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWrote 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/slbug/claude-ruby-grape-rails/pr-review)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/pr-review"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/pr-review.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 | $0.00056 | $0.01070 |
| Opus 5 | $0.00028 | $0.00535 |
| Sonnet 5 | $0.00011 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
rb:pr-review 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.
This is a copy
86% identical to elixir-phoenix-pr-review — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Response
Fetch PR review comments, categorize them, draft responses, and optionally apply code fixes.
Usage
/rb:pr-review 42 # Address comments on PR #42
/rb:pr-review 42 --fix # Address + apply code fixes
/rb:pr-review https://... # Full URL also works
Arguments
$ARGUMENTS = PR number (or URL), optionally followed by --fix.
Workflow
Step 1: Fetch PR Context
Fetch PR context:
- Run
gh pr view {number} --json title,body,state,baseRefName,headRefNamefor metadata - Run
gh api repos/{owner}/{repo}/pulls/{number}/comments --paginatefor inline comments - Run
gh api repos/{owner}/{repo}/pulls/{number}/reviews --paginatefor review data - Run
gh pr diff {number}for the diff
Parse the PR number from $ARGUMENTS. If a URL, extract the
number from it. Detect --fix flag.
Step 2: Categorize Comments
Group each comment into one of these categories:
| Category | Signal | Action |
|---|---|---|
| Code change | "should be", "change to", "use X instead" | Draft fix + response |
| Question | "why", "what if", "how does" | Draft explanation |
| Nitpick | "nit:", style-only, formatting | Quick acknowledgment |
| Praise | "nice", "good", "LGTM" | No action needed |
| Discussion | Architecture, trade-offs, alternatives | Draft thoughtful response |
Step 3: Map to Code Locations
For each code-change comment:
- Find the file and line from the comment's
pathandposition - Read the current code at that location
- Understand the reviewer's suggestion in context
- Check if the suggestion conflicts with Iron Laws
Step 4: Draft Responses
For each comment, draft a response following patterns in
references/response-patterns.md.
Present ALL draft responses to the user for review:
## PR #{number}: {title}
### {n} comments to address
**Code changes ({n}):**
1. {file}:{line} — {reviewer suggestion} → {proposed fix}
**Questions ({n}):**
1. {question summary} → {draft answer}
**Nitpicks ({n}):**
1. {nit} → Acknowledged
**Discussion ({n}):**
1. {topic} → {draft response}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 139 lines · 56 tokens per session scan A 377b959bea8f
rb:pr-review is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 1,070 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to elixir-phoenix-pr-review, differing in 38 lines, and is treated as a copy.
Other skills, from other repositories
contribute
Complete contribution workflow using git-town. Create branch → commit → PR → ship. Preflight at every step.
git-workflow
Git workflow and conventional commits. Use when working with git, branches, commits, pull requests, code review, or version control strategy.
lenserfighter
Autonomous open-source contributor that reviews PRs, triages and opens issues, and drafts minimal fix PRs for the LenserFight monorepo — without merging.
github
GitHub-centric templates — pull requests, issue triage, repo automation.
pr-review-fix-pipeline
Autonomous PR review that also applies fixes for non-controversial issues — combines review, fix, test, and commit into a single pipeline. Unlike a read-only review, this writes code. Only use on feature branches where you're comfortable with automatic edits. Trigger on: "review and fix PR", "auto-fix the PR", "clean…
pr-review
From diff to reviewer-ready summary — analyze, review, surface risks, draft PR description.