Agent skill

Subagent Review

by NikiforovAll in NikiforovAll/claude-code-rules

Review changed code for reuse, quality, and efficiency using three parallel disposable subagents.

Apache-2.0Auto-check passedDevelopment

Install Subagent Review

skills CLI
$ npx skills add NikiforovAll/claude-code-rules --skill subagent-review -a claude-code

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

GitHub CLI
$ gh skill install NikiforovAll/claude-code-rules subagent-review --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/NikiforovAll/claude-code-rules.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/handbook-code-review/skills/subagent-review .claude/skills/subagent-review && 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
subagent-review
GitHub stars
141
Token cost
~927 tokens
SKILL.md length
476 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
Apache-2.0

At a glance

Review changed code for reuse, quality, and efficiency using three parallel disposable subagents.

  • Works in 3 steps: Identify Changes → Launch Three Review Agents in Parallel → Fix Issues
  • Wants a one-shot code review without persistent reviewers
  • SKILL.md covers Phase 1: Identify Changes, Phase 2: Launch Three Review… and Phase 3: Fix Issues
  • Calls git

What it does

Subagent Review is an agent skill from NikiforovAll/claude-code-rules. Review changed code for reuse, quality, and efficiency using three parallel disposable subagents. This skill should be used when the user says "review", "simplify", "code review", or wants a one-shot code review without persistent reviewers.

Its SKILL.md is about 930 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 Subagents, Code simplification and Code review. It works with Git. The repository describes itself as: Learn practical techniques to enhance your AI-assisted development workflow with Claude Code. The licence is Apache-2.0.

When your agent uses it

  • Wants a one-shot code review without persistent reviewers
  • Tasks that involve Subagents
  • Tasks that involve Code simplification

Example prompts

  • “review”
  • “simplify”
  • “code review”
  • “/subagent-review”

Requirements

  • Pre-approved tools (allowed-tools): Agent, Bash(git diff *), Bash(git log *), Bash(git status *), Read, Grep, Glob

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Identify Changes
  2. Launch Three Review Agents in Parallel
  3. Fix Issues

What it can do on your machine

Read from SKILL.md and the folder at commit 281c063. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Agent
    • Bash(git diff *)
    • Bash(git log *)
    • Bash(git status *)
    • Read
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Subagent Review loads about 927 tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 476 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~927

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 NikiforovAll/claude-code-rules at commit 281c063, republished under its Apache-2.0 licence (© NikiforovAll). 476 words, ~927 tokens.

Download SKILL.mdSave it as .claude/skills/subagent-review/SKILL.md (or your agent's skills folder).
name
subagent-review
description
Review changed code for reuse, quality, and efficiency using three parallel disposable subagents. This skill should be used when the user says "review", "simplify", "code review", or wants a one-shot code review without persistent reviewers.
allowed-tools
Agent, Bash(git diff *), Bash(git log *), Bash(git status *), Read, Grep, Glob

Subagent Review: One-Shot Code Review

Review all changed files for reuse, quality, and efficiency. Fix any issues found.

Phase 1: Identify Changes

Run git diff (or git diff HEAD if there are staged changes) to see what changed. If there are no git changes, review the most recently modified files that the user mentioned or that you edited earlier in this conversation.

Phase 2: Launch Three Review Agents in Parallel

Use the Agent tool to launch all three agents concurrently in a single message. Pass each agent the full diff so it has the complete context.

Agent 1: Code Reuse Review

For each change:

  1. Search for existing utilities and helpers that could replace newly written code. Look for similar patterns elsewhere in the codebase — common locations are utility directories, shared modules, and files adjacent to the changed ones.
  2. Flag any new function that duplicates existing functionality. Suggest the existing function to use instead.
  3. Flag any inline logic that could use an existing utility — hand-rolled string manipulation, manual path handling, custom environment checks, ad-hoc type guards, and similar patterns are common candidates.
Agent 2: Code Quality Review

Review the same changes for hacky patterns:

  1. Redundant state: state that duplicates existing state, cached values that could be derived, observers/effects that could be direct calls
  2. Parameter sprawl: adding new parameters to a function instead of generalizing or restructuring existing ones
  3. Copy-paste with slight variation: near-duplicate code blocks that should be unified with a shared abstraction
  4. Leaky abstractions: exposing internal details that should be encapsulated, or breaking existing abstraction boundaries
  5. Stringly-typed code: using raw strings where constants, enums (string unions), or branded types already exist in the codebase
  6. Unnecessary nesting: wrapper elements that add no layout value
  7. Unnecessary comments: comments explaining WHAT the code does — delete; keep only non-obvious WHY (hidden constraints, subtle invariants, workarounds)
Show full SKILL.md (165 more words)Show less
Agent 3: Efficiency Review

Review the same changes for efficiency:

  1. Unnecessary work: redundant computations, repeated file reads, duplicate network/API calls, N+1 patterns
  2. Missed concurrency: independent operations run sequentially when they could run in parallel
  3. Hot-path bloat: new blocking work added to startup or per-request/per-render hot paths
  4. Recurring no-op updates: state/store updates that fire unconditionally — add change-detection guards so downstream consumers aren't notified when nothing changed
  5. Unnecessary existence checks: pre-checking file/resource existence before operating (TOCTOU anti-pattern) — operate directly and handle the error
  6. Memory: unbounded data structures, missing cleanup, event listener leaks
  7. Overly broad operations: reading entire files when only a portion is needed, loading all items when filtering for one

Phase 3: Fix Issues

Wait for all three agents to complete. Aggregate their findings and fix each issue directly. If a finding is a false positive or not worth addressing, note it and move on.

When done, briefly summarize what was fixed (or confirm the code was already clean).

© NikiforovAll, Apache-2.0. 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 plugins/handbook-code-review/skills/subagent-review of NikiforovAll/claude-code-rules.

Open the folder on GitHubat commit 281c063

Compare with similar skills

Subagent Review 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.

Subagent Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Subagent Review this skillNikiforovAll/claude-code-rules141—~927Automated safety check: PassApache-2.0
Review And Simplify ChangesDimillian/Skills4k—~2kAutomated safety check: PassMIT
Simplify Codesickn33/agentic-awesome-skills47k2 repos~1.8kAutomated safety check: PassMIT
Cursor Composer Task DelegateChachamaru127/claude-code-harness3.2k—~4.4kAutomated safety check: NotesMIT
Ad ReviewCorridorTech/PoseCap224—~2.4kAutomated safety check: NotesApache-2.0
Workflow Code ReviewdavidYichengWei/agentic-engineering-framework158—~1.1kAutomated safety check: PassMIT

Similar skills

  • Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes.

    4k GitHub stars~2k tokensUpdated 6 mo ago
    DevelopmentAuto-check passed
  • Simplify Code

    sickn33/agentic-awesome-skills

    Review a diff for clarity and safe simplifications, then optionally apply low-risk fixes.

    47k GitHub starsUsed in 2 repos~1.8k tokens
    DevelopmentAuto-check passed
  • Cursor Composer Task Delegate

    Chachamaru127/claude-code-harness

    Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.

    3.2k GitHub stars~4.4k tokensUpdated 6 days ago
    DevelopmentAuto-check: notes
  • Ad Review

    CorridorTech/PoseCap

    Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

    224 GitHub stars~2.4k tokensUpdated 4 days ago
    DevelopmentAuto-check: notes
  • Workflow Code Review

    davidYichengWei/agentic-engineering-framework

    代码评审。协调 5 个专项 reviewer subagent 对代码进行并行多维度审查。可由用户直接触发,也可由主 agent 加载后作为 Judge 执行。

    158 GitHub stars~1.1k tokensUpdated 6 mo ago
    DevelopmentAuto-check passed
  • Specialist Review

    hanamizuki/solopreneur

    Tech-stack-aware expert code review using specialized subagents.

    152 GitHub stars~3k tokensUpdated 14 days ago
    DevelopmentAuto-check passed

More from NikiforovAll/claude-code-rules

All 26 skills in this repo
  • Reflect Solution

    NikiforovAll/claude-code-rules

    Summarize WHAT WAS SHIPPED in a Claude Code session as a self-contained HTML slide deck — the elevator pitch (problem, solution, decisions, artifacts, verification, gaps), not a play-by-play of tool…

    141 GitHub stars~3.8k tokensUpdated 8 days ago
    Auto-check passed
  • Dotnet Analyzers

    NikiforovAll/claude-code-rules

    Run dotnet format to fix code style and analyzer diagnostics (IDE0005, CA, SA).

    141 GitHub stars~1.9k tokensUpdated 8 days ago
    Auto-check passed
  • Ilspy Decompile

    NikiforovAll/claude-code-rules

    Understand implementation details of .NET code by decompiling assemblies.

    141 GitHub starsUsed in 2 repos~760 tokens
    Auto-check passed
  • Reflect Tree

    NikiforovAll/claude-code-rules

    Visualize a Claude Code session as a quest/skill tree — a navigable SVG graph where nodes are turns and edges show flow, with distinct visual encoding for normal flow, dead-ends, corrections…

    141 GitHub stars~2.8k tokensUpdated 8 days ago
    Auto-check passed
  • Structured Plan Mode

    NikiforovAll/claude-code-rules

    This skill should be used when planning and tracking complex feature implementations that require systematic task decomposition.

    141 GitHub stars~4.2k tokensUpdated 8 days ago
    Auto-check passed
  • Glab

    NikiforovAll/claude-code-rules

    Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line.

    141 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Works with

Questions about Subagent Review

What does Subagent Review do?

Review changed code for reuse, quality, and efficiency using three parallel disposable subagents. Subagent Review is an agent skill from NikiforovAll/claude-code-rules. Review changed code for reuse, quality, and efficiency using three parallel disposable subagents.

When should I use Subagent Review?

Subagent Review fits situations like: wants a one-shot code review without persistent reviewers; tasks that involve Subagents; tasks that involve Code simplification.

How do I install Subagent Review in Claude Code?

Run `npx skills add NikiforovAll/claude-code-rules --skill subagent-review -a claude-code`. Or copy the skill folder (plugins/handbook-code-review/skills/subagent-review in NikiforovAll/claude-code-rules) into .claude/skills/subagent-review in your project. Claude Code loads it when a task matches its description.

How do I install Subagent Review in Codex?

Run `npx skills add NikiforovAll/claude-code-rules --skill subagent-review -a codex`. Or copy the skill folder (plugins/handbook-code-review/skills/subagent-review in NikiforovAll/claude-code-rules) into .agents/skills/subagent-review in your project. Codex loads it when a task matches its description.

Can I use Subagent Review 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 NikiforovAll/claude-code-rules --skill subagent-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/subagent-review, .gemini/skills/subagent-review, .github/skills/subagent-review and .opencode/skills/subagent-review in your project.

What does Subagent Review need to run?

Going by SKILL.md and its folder, Subagent Review needs the command-line tools its instructions call (git). Its frontmatter pre-approves these tools: Agent, Bash(git diff *), Bash(git log *), Bash(git status *), Read, Grep, Glob.

Does Subagent Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Subagent Review 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 Subagent Review use?

Subagent Review is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Subagent Review use?

About 927 tokens (SKILL.md is roughly 3.7k 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 Subagent Review?

Skills that share tags, products or a category with Subagent Review: Review And Simplify Changes (Dimillian/Skills, 4k stars), Simplify Code (sickn33/agentic-awesome-skills, 47k stars), Cursor Composer Task Delegate (Chachamaru127/claude-code-harness, 3.2k stars) and Ad Review (CorridorTech/PoseCap, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Subagent Review?

NikiforovAll (a GitHub user) maintains it in NikiforovAll/claude-code-rules, which has 141 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 2, 2026.

Source: NikiforovAll/claude-code-rules on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.