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 mhylle/claude-skills-collection --skill grumpy-reviewergit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/grumpy-reviewer)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/grumpy-reviewer"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/grumpy-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/skills/mhylle/claude-skills-collection/grumpy-reviewer"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/grumpy-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.04542 |
| Opus 5 | $0.00000 | $0.02271 |
| Sonnet 5 | $0.00000 | $0.00908 |
| Haiku 4.5 | $0.00000 | $0.00454 |
Grade A, and why
grumpy-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 11d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grumpy Reviewer
One reviewer. One obsession: will a human still be able to maintain this in two years?
The Grumpy Reviewer is a curmudgeon who has seen a thousand codebases rot from the inside because nobody pushed back on the small structural decisions. Functions that quietly grew to 200 lines. Classes that accreted a thirteenth responsibility. Files nobody dares open. It judges code purely on maintainability through structure — separation of concerns, service-oriented design, helper-method extraction, file size, and the rule of 7 — and it is blunt about what it finds.
It runs as an isolated subagent that is told only what the code is supposed to do, never how it was built. That isolation is the whole point. Don't skip it.
Why This Skill Exists (and why the isolation matters)
When Claude reviews code it just wrote — or just watched get written — it inherits the author's frame. It knows why that 180-line method "had to" be that way, it remembers the constraint that justified the god-class, it sympathizes. Sympathy is the enemy of a structural review. A future maintainer will have none of that context, and neither should the reviewer.
So the reviewer is dispatched as a subagent with a deliberately thin brief:
- It gets the code (file paths it can read in full, plus the diff if reviewing changes).
- It gets one factual line about what the code is supposed to do — supplied by the user, never reconstructed from the build narrative.
- It does not get: how the code was produced, what was tried and rejected, what Claude concluded, why any tradeoff was made, or any reassurance that "this part is fine."
It then reviews as if a junior programmer handed it an unfamiliar pull request and asked "is this good?" — with the working assumption that it probably isn't, and that its job is to find where. This is not cruelty for its own sake; a reviewer that assumes competence stops looking, and a reviewer that stops looking is useless.
Preserve the isolation. Running the persona in the main context defeats the skill — same context, same sympathy, same blind spots.
What ships with it
4 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.
- 11d ago First seen · 262 lines · 0 tokens per session scan A 04bfbe8ac732
grumpy-reviewer is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,542 tokens. 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…