Agent skill

Code Reviewer

by criptogus in criptogus/agent-evolve-network

Reviews a code diff and returns prioritized, actionable feedback grouped by severity.

CC-BY-SA-4.0Auto-check passedDevelopment

Install Code Reviewer

skills CLI
$ npx skills add criptogus/agent-evolve-network --skill code-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install criptogus/agent-evolve-network code-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/criptogus/agent-evolve-network.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/code-reviewer .claude/skills/code-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-reviewer
GitHub stars
288
Token cost
~820 tokens
SKILL.md length
204 words
Files
1
Skills in repo
107
Repo updated
First seen
Licence
CC-BY-SA-4.0

At a glance

Reviews a code diff and returns prioritized, actionable feedback grouped by severity.

  • Works in 3 steps: Blocking (correctness/security) → Should fix (perf/maintainability) → Nits (style/naming)
  • The user asks for pragmatic code reviewer work
  • SKILL.md covers Instructions, Always, Never and Input / output contract, plus 6 more sections
  • Reaches superagentskill.com

What it does

Code Reviewer is an agent skill from criptogus/agent-evolve-network. Reviews a code diff and returns prioritized, actionable feedback grouped by severity. Use when the user asks for pragmatic code reviewer work, or mentions code, reviewer.

Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review. The licence is CC-BY-SA-4.0.

When your agent uses it

  • The user asks for pragmatic code reviewer work
  • Tasks that involve Code review

Example prompts

  • “Use the code-reviewer skill to review a code diff and returns prioritized, actionable feedback grouped by severity”
  • “/code-reviewer”

Requirements

  • Node.js

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Blocking (correctness/security)
  2. Should fix (perf/maintainability)
  3. Nits (style/naming)

What it can do on your machine

Read from SKILL.md and the folder at commit d19b920. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json and typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • superagentskill.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Code Reviewer loads about 820 tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 204 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~820

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from criptogus/agent-evolve-network at commit d19b920, republished under its CC-BY-SA-4.0 licence (© criptogus). 204 words, ~820 tokens.

Download SKILL.mdSave it as .claude/skills/code-reviewer/SKILL.md (or your agent's skills folder).
name
code-reviewer
description
Reviews a code diff and returns prioritized, actionable feedback grouped by severity. Use when the user asks for pragmatic code reviewer work, or mentions code, reviewer.
version
0.1.0
license
CC-BY-SA-4.0
homepage
https://superagentskill.com/marketplace/code-reviewer
source
Super Agent Skill (SAK)

Pragmatic Code Reviewer

Use this skill when you have a unified diff (git format) and want a focused review. It flags correctness, security, performance and readability issues, and suggests concrete rewrites. It does NOT run the code or guess at intent beyond what the diff shows.

Instructions

You are a senior engineer doing a pull-request review. You receive a unified diff. Produce feedback grouped under exactly these headings, in this order:

  1. Blocking (correctness/security)
  2. Should fix (perf/maintainability)
  3. Nits (style/naming) For every item, include: file:line, the problem in one sentence, and a suggested patch in a fenced code block. If a section has no items, write "None". Never invent code that is not in the diff. Never lecture about general best practices.

Always

  • Reference exact file:line from the diff for every comment.
  • Keep each comment under 4 sentences.
  • Use the three fixed sections.

Never

  • Suggest changes outside the diff.
  • Repeat the same issue across sections.
  • Praise the author or add filler.

Input / output contract

Input:

json
{
  "type": "object",
  "properties": {
    "diff": {
      "type": "string",
      "description": "unified diff"
    },
    "context": {
      "type": "string",
      "description": "optional PR description"
    }
  },
  "required": [
    "diff"
  ]
}

Output:

json
{
  "type": "object",
  "properties": {
    "markdown": {
      "type": "string"
    }
  },
  "required": [
    "markdown"
  ]
}

Examples

Off-by-one in a loop

Input:

diff --git a/util.ts b/util.ts
@@ -3,5 +3,5 @@ export function lastN<T>(arr: T[], n: number) {
-  return arr.slice(arr.length - n);
+  return arr.slice(arr.length - n - 1);
 }

Expected output:

## Blocking
- **util.ts:5** — Off-by-one: `arr.length - n - 1` returns `n + 1` items.
  ```ts
  return arr.slice(arr.length - n);

Should fix

None

Nits

None


Why: One clear blocking issue, exact line cited, suggested patch included.

### Clean diff, only nit

Input:

diff --git a/api.ts b/api.ts @@ -10,2 +10,2 @@ -const URL='https://api.example.com' +const apiURL = 'https://api.example.com'


Expected output:

Blocking

None

Should fix

None

Nits

  • api.ts:11 — Prefer API_URL (SCREAMING_SNAKE_CASE) for module-level constants.
    ts
    const API_URL = 'https://api.example.com';

## Trust & telemetry

This skill is graded on the Super Agent Skill network: format, substance and adversarial
(prompt-injection) testing produce a public Trust Score.

- Trust Score & evidence: https://superagentskill.com/marketplace/trust/code-reviewer
- Skill page: https://superagentskill.com/marketplace/code-reviewer
- Live version (always current) via MCP: https://superagentskill.com/api/mcp

Reinstall or update with `npx skills update`, or pull the live graded version with
`npx super-agent install code-reviewer`.

© criptogus, CC-BY-SA-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/code-reviewer of criptogus/agent-evolve-network.

Open the folder on GitHubat commit d19b920

Compare with similar skills

Code Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Reviewer this skillcriptogus/agent-evolve-network288—~820Automated safety check: PassCC-BY-SA-4.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow156k—~3.5kAutomated safety check: NotesMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything85k1 repos~1.4kAutomated safety check: PassMIT
Mole Bug Patternstw93/Mole69k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    85k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    69k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

More from criptogus/agent-evolve-network

All 107 skills in this repo
  • Brand Research

    criptogus/agent-evolve-network

    Kickoff research for a brand you haven't worked on before — web research, existing-ad analysis from the Meta Ad Library, editorial-grammar profiling, sourced + AI-generated brand assets, hook/CTA…

    288 GitHub stars~3.9k tokensUpdated 27 days ago
    Auto-check passed
  • Create Apple Notes Video Ad

    criptogus/agent-evolve-network

    Produce a 9:16 social-native ad recreating the iPhone Apple Notes typing experience — the note begins with 1–2 visible lines, then progressively types additional paragraphs character-by-character…

    288 GitHub stars~4.9k tokensUpdated 27 days ago
    Auto-check passed
  • Create Chatgpt Video Ad

    criptogus/agent-evolve-network

    Produce a 9:16 social-native ad that recreates a ChatGPT mobile chat — user types in the composer with the iOS keyboard visible, taps send, keyboard slides down, header right-cluster swaps…

    288 GitHub stars~5k tokensUpdated 27 days ago
    Auto-check passed
  • Create Imessage Video Ad

    criptogus/agent-evolve-network

    Produce a 9:16 social-native ad that recreates an iMessage conversation reveal — bubbles pop in over time, composer types char-by-char, real Apple iMessage SFX hit on every send/receive, music bed…

    288 GitHub stars~7.4k tokensUpdated 27 days ago
    Auto-check passed
  • Cloud Misconfig Auditor

    criptogus/agent-evolve-network

    Audits AWS, GCP and Azure environments (and matching IaC) for excessive permissions, public exposure, weak encryption defaults and missing logging.

    288 GitHub stars~965 tokensUpdated 27 days ago
    Auto-check passed
  • Cloudflare Workers Expert

    criptogus/agent-evolve-network

    Builds and debugs Cloudflare Workers, Durable Objects, KV, R2, D1, and Queues with edge-correct patterns.

    288 GitHub stars~619 tokensUpdated 27 days ago
    Auto-check passed

Categories

Questions about Code Reviewer

What does Code Reviewer do?

Reviews a code diff and returns prioritized, actionable feedback grouped by severity. Code Reviewer is an agent skill from criptogus/agent-evolve-network. Reviews a code diff and returns prioritized, actionable feedback grouped by severity.

When should I use Code Reviewer?

Code Reviewer fits situations like: the user asks for pragmatic code reviewer work; tasks that involve Code review.

How do I install Code Reviewer in Claude Code?

Run `npx skills add criptogus/agent-evolve-network --skill code-reviewer -a claude-code`. Or copy the skill folder (skills/code-reviewer in criptogus/agent-evolve-network) into .claude/skills/code-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Code Reviewer in Codex?

Run `npx skills add criptogus/agent-evolve-network --skill code-reviewer -a codex`. Or copy the skill folder (skills/code-reviewer in criptogus/agent-evolve-network) into .agents/skills/code-reviewer in your project. Codex loads it when a task matches its description.

Can I use Code Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add criptogus/agent-evolve-network --skill code-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-reviewer, .gemini/skills/code-reviewer, .github/skills/code-reviewer and .opencode/skills/code-reviewer in your project.

What does Code Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Reviewer is instructions for the agent only. Our summary lists: Node.js.

Does Code Reviewer access the network?

SKILL.md names 1 domain. In commands or code: superagentskill.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Code Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Reviewer use?

Code Reviewer is published under the CC-BY-SA-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Reviewer use?

About 820 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Code Reviewer?

Skills that share tags, products or a category with Code Reviewer: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 85k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Reviewer?

criptogus (a GitHub user) maintains it in criptogus/agent-evolve-network, which has 288 GitHub stars. The repository holds 107 skills in this directory. The repository was last updated on September 9, 2026.

Source: criptogus/agent-evolve-network on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.