review-rubric

review-rubric is a skill for Claude Code, Codex from LingoVerse/mimir. It costs 35 tokens per session (986 once invoked), scanned A, original, MIT.

A checklist and writing format for reviewing pull requests, which are proposed code changes awaiting approval. It ranks findings such as bugs, security problems, data risks, failures, and broken interfaces by severity.

In plain words
What is it for?
Checking pull-request correctness, security, data handling, resource cleanup, API compatibility, and error paths, then reporting important issues in a consistent format.
Why use it?
It helps reviewers focus on problems that could affect users or the project instead of filling reviews with minor style comments. It also makes findings specific and actionable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Checking pull-request correctness, security, data handling, resource cleanup, API compatibility, and error paths, then reporting important issues in a consistent format.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lingoverse/mimir/review-rubric
Install

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.

Any agent
npx skills add LingoVerse/mimir --skill review-rubric
Clone the repo
git clone --depth 1 https://github.com/LingoVerse/mimir

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for review-rubric

README.md
[![agentmods](https://agentmods.dev/badge/skills/lingoverse/mimir/review-rubric/github.svg)](https://agentmods.dev/skills/lingoverse/mimir/review-rubric)
Your own site
<a href="https://agentmods.dev/skills/lingoverse/mimir/review-rubric"><img src="https://agentmods.dev/badge/skills/lingoverse/mimir/review-rubric/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.

agentmods 80×15 button for review-rubric

Your own site · 80×15
<a href="https://agentmods.dev/skills/lingoverse/mimir/review-rubric"><img src="https://agentmods.dev/badge/skills/lingoverse/mimir/review-rubric.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 986 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00986
Opus 5 $0.00017 $0.00493
Sonnet 5 $0.00007 $0.00197
Haiku 4.5 $0.00003 $0.00099

Measured 8d ago against content hash b17991d384ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-rubric 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 8d 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.

src/skills/review-rubric/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Rubric

You are reviewing a pull request diff. Your job is to find issues that genuinely matter and explain them clearly. A good reviewer is trusted because they are precise — they do not drown real problems in nitpicks. Bias toward fewer, higher-quality comments.

What to review (in priority order)

  1. Correctness — logic errors, off-by-one, wrong conditionals, unhandled error paths, race conditions, incorrect async/await, broken edge cases, misuse of APIs.
  2. Security — injection (SQL/command/template), missing authz/authn checks, secrets in code, unsafe deserialization, SSRF, path traversal, unvalidated input crossing a trust boundary. (A dedicated security-check skill goes deeper when sensitive paths change.)
  3. Data & state — migrations that lose data or aren't reversible, N+1 queries, missing indexes implied by new query patterns, cache/invalidation bugs, money/precision handling.
  4. Resource & failure handling — leaks (connections, file handles, timers), missing timeouts/retries, unbounded growth, swallowed errors.
  5. API & contract — breaking changes to public interfaces, inconsistent error shapes, backward-incompatible schema changes without versioning.
  6. Tests — new logic landing with no test; tests that assert nothing; deleted tests.
  7. Readability & maintainability — only when it materially hurts comprehension or future change. Naming, dead code, duplicated logic worth extracting.

Severity scale

  • critical — will break production, lose/corrupt data, or open a security hole. Must fix before merge. Be conservative: only use critical when you're confident.
  • major — likely bug, real security weakness, or significant maintainability problem. Should fix before merge.
  • minor — small bug, edge case, or clarity issue. Fix recommended, not blocking.
  • nit — style/preference. Suppressed by default; only emit if explicitly enabled.

What NOT to comment on

  • Formatting/style already enforced by a linter or formatter (Prettier/ESLint/etc.).
  • Personal style preferences dressed up as problems.
  • Things outside the diff (don't review unchanged code unless the diff clearly breaks it).
  • Generated, vendored, lockfile, or minified content.
  • Repeating the same finding on every occurrence — state it once, note "applies to N places".
  • Praise-only comments. A short positive note in the summary is fine; inline praise is noise.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 8d ago First seen · 88 lines · 35 tokens per session scan A b17991d384ab

Subscribe to this mod's changes

review-rubric is a skill published in the GitHub repository LingoVerse/mimir (5 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 986 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

open-code-review-delegate

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

alibaba/open-code-review · 68 tokens

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…

alibaba/open-code-review · 98 tokens

md-audit

Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…

chaitanyagiri/munder-difflin · 85 tokens

code-review

Paranoid architect review of code changes for bugs, security, missing tests, and undocumented assumptions. Works on local git diffs OR a GitHub pull request (e.g. owner/repo N). For PRs, can post findings as line-level review comments.

suyoumo/ClawProBench · 57 tokens

parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

suyoumo/ClawProBench · 67 tokens

qa-review

QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.

suyoumo/ClawProBench · 30 tokens