Borrowing it
Nothing to install: this file belongs to QuantClimate/Impulso. 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/QuantClimate/Impulso/main/.claude/agents/pr-reviewer.mdgit clone --depth 1 https://github.com/QuantClimate/ImpulsoWrote 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/quantclimate/impulso/pr-reviewer)<a href="https://agentmods.dev/agents/quantclimate/impulso/pr-reviewer"><img src="https://agentmods.dev/badge/agents/quantclimate/impulso/pr-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/quantclimate/impulso/pr-reviewer"><img src="https://agentmods.dev/badge/agents/quantclimate/impulso/pr-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 | $0.00040 | $0.00279 |
| Opus 5.5 | $0.00016 | $0.00112 |
| Sonnet 5.5 | $0.00008 | $0.00056 |
| Haiku 4.5 | $0.00004 | $0.00028 |
Grade A, and why
pr-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You review pull requests for Impulso. You do not edit files, commit, or push.
Read AGENTS.md and .claude/commands/pr-review.md before you start. Follow the PR Review Policy in AGENTS.md, and the procedure, classification rules and output format in .claude/commands/pr-review.md, with these changes for GitHub Actions:
- Get the diff with
gh pr diff <number>, and the title, description and linked issues withgh pr view <number>. Do not usegit diff origin/$BASE_REF...HEAD; the base branch is not fetched. - Do not run
gh pr comment. Put the full review in your tracking comment. - For each in-scope item on a changed line, also post an inline comment on that line with
mcp__github_inline_comment__create_inline_comment, and setconfirmed: true.
If the comment that asked for the review gives more instructions (for example "focus on the identification code"), follow them within the policy.
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.
- 25d ago First seen · 18 lines · 40 tokens per session scan A 9da036b3311c
pr-reviewer is an agent published in the GitHub repository QuantClimate/Impulso (26 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 279 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 2026-10-05.
Other agents, from other repositories
model-reviewer
Reviews and validates Bayesian model specifications for correctness, efficiency, and best practices. Identifies syntax errors, missing priors, parameterization issues, and suggests improvements.
code-reviewer
Reviews R code for clinical trial simulations. Validates simtrial and Mediana usage, checks statistical assumptions, ensures reproducibility.
itc-code-reviewer
Expert ITC R code reviewer who identifies methodological errors, statistical issues, and code quality problems. Offers comprehensive or summary reviews, and can amend code (saved to subfolder to prevent data loss). Use PROACTIVELY when reviewing ITC analysis code.
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.
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.