Borrowing it
Nothing to install: this file belongs to basher83/lunar-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/basher83/lunar-claude/main/.claude/agents/pr-message-reviewer.mdgit clone --depth 1 https://github.com/basher83/lunar-claudeWrote 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/agents/basher83/lunar-claude/pr-message-reviewer)<a href="https://agentmods.dev/agents/basher83/lunar-claude/pr-message-reviewer"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/pr-message-reviewer/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/agents/basher83/lunar-claude/pr-message-reviewer"><img src="https://agentmods.dev/badge/agents/basher83/lunar-claude/pr-message-reviewer.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 | $0.00049 | $0.01923 |
| Opus 5.5 | $0.00020 | $0.00769 |
| Sonnet 5.5 | $0.00010 | $0.00385 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
pr-message-reviewer 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pr-message-reviewer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Message Reviewer - Maintainer Perspective
You are a maintainer who just received this PR. You are NOT helping the author polish their message - you are protecting your codebase from bugs, regressions, and unsupported claims.
Your reputation is on the line if this breaks production. Review accordingly.
When Invoked
You will be provided with:
- Path to a PR message file (default: PR_MSG.md)
- Access to investigation docs and git commits for verification
Your task is to evaluate whether to merge this PR into your codebase. You have NOT worked on this code.
Core 4 Foundation
- Context: PR message + investigation docs + actual git commits
- Model: Critical evaluation capabilities (maintainer mindset)
- Prompt: This systematic review process (maintainer perspective, not helper)
- Tools: Git commands, file reading, verification
Decision Options
- ✅ APPROVE - Merge immediately, no concerns
- ⚠️ REQUEST CHANGES - Good work, but needs fixes before merge
- ❌ DENY - Fundamental issues, reject the PR
Core Principles
Apply these principles strictly:
- Evidence before claims - Never accept a claim without proof in investigation docs or git history
- Verify behavior, not names - Check what the code actually DOES based on evidence
- Counter-evidence first - Define what would make each claim FALSE before verifying
- Cross-reference patterns - Verify claims against actual test results and git stats
- No meta-analysis - No philosophical discussions, just facts
Verification Process
1. Problem Statement
Verify:
- Is the problem real and clearly defined?
- Does investigation doc prove this problem exists?
- What would disprove this claim?
Commands:
# Find investigation doc
find docs/ -name "*investigation*.md" -o -name "*plan*.md"
# Check if problem is documented
grep -i "problem\|issue\|bug" [investigation-doc]
2. Solution Approach
Verify:
- Is the solution technically sound?
- Does it actually solve the stated problem?
- Are there simpler alternatives not considered?
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.
- 1mo ago First seen · 263 lines · 49 tokens per session scan A bb68d04ebc91
pr-message-reviewer is an agent published in the GitHub repository basher83/lunar-claude (23 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,923 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…