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 luabagg/agent-skills --skill thorough-pr-reviewgit clone --depth 1 https://github.com/luabagg/agent-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/luabagg/agent-skills/thorough-pr-review)<a href="https://agentmods.dev/skills/luabagg/agent-skills/thorough-pr-review"><img src="https://agentmods.dev/badge/skills/luabagg/agent-skills/thorough-pr-review/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/luabagg/agent-skills/thorough-pr-review"><img src="https://agentmods.dev/badge/skills/luabagg/agent-skills/thorough-pr-review.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 | $0.00073 | $0.01073 |
| Opus 5 | $0.00036 | $0.00536 |
| Sonnet 5 | $0.00015 | $0.00215 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
thorough-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 6d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thorough PR Review
Review a code change for correctness, reliability, and scope alignment. Back each finding with evidence.
When NOT to use
- Tiny changes. A one-line typo or doc fix does not need the full template. One sentence is the right answer.
- Mid-conflict PRs. If the branch is being rebased or has unresolved conflicts, wait.
- Re-reviewing unchanged code. If the PR has not changed since a prior review, say so and stop.
- Pure security audit. Use
security-reviewinstead.
Anti-hallucination rule
Review framing biases agents toward finding problems. Resist it.
- If the change is small, correct, and follows convention, say so and stop. A three-line PR deserves a three-line review.
- Do not pad the output with nitpicks. Each Low item must be useful.
- When uncertain, label the finding as a hypothesis. Say what would confirm or refute it.
Workflow
1. Determine scope
If given a PR URL or number, extract the number from /pull/<N> and run:
gh pr view <number-or-url> --json title,body,url,number,files,commits,baseRefName,headRefName,reviews,comments
gh pr checks <number-or-url>
reviews and comments show whether someone already reviewed. Do not repeat their findings. checks shows what CI already caught.
If no PR is given, review the local branch:
git status
git branch --show-current
git log --oneline <base-branch>..HEAD
git diff <base-branch>...HEAD
2. Gather intent
Read the PR title and body. If a linked issue or ticket is mentioned, fetch it. You review against stated intent. If intent is missing or unclear, ask the user before you continue.
3. Read in context
For each changed file, read the modified sections with their surroundings: adjacent functions, callers, tests, configs. A line can look wrong in isolation and be correct in context, or the reverse.
4. Evaluate
Walk the change through the heuristics in references/heuristics.md. Each heuristic is a concrete check ("flag a new abstraction with only one caller"), not a principle ("apply SRP"). Apply the checks that fit the change type. Do not scan all ten on a 20-line PR.
What ships with it
3 files 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.
- 6d ago Changed · -17 lines 1215b0654ba1
- 10d ago First seen · 122 lines · 73 tokens per session scan A e6497c2a3e29
thorough-pr-review is a skill published in the GitHub repository luabagg/agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 1,073 once invoked, about $0.0004 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
evaluator-review-contract
Internal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".