Agent skill

Review Swarm

by Dimillian in Dimillian/Skills

Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test…

MITAuto-check passedAgent Workflows

Install Review Swarm

skills CLI
$ npx skills add Dimillian/Skills --skill review-swarm -a claude-code

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

GitHub CLI
$ gh skill install Dimillian/Skills review-swarm --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/Dimillian/Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/review-swarm .claude/skills/review-swarm && 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
review-swarm
GitHub stars
4k
Token cost
~1.6k tokens
SKILL.md length
940 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test…

  • Works in 5 steps: Determine Scope and Intent → Launch Four Read-Only Reviewers in… → Aggregate and Filter Findings → …
  • The user asks for a review swarm
  • SKILL.md covers Step 1: Determine Scope and…, Step 2: Launch Four Read-Only…, Step 3: Aggregate and Filter… and Step 4: Order the Output, plus 1 more section
  • Calls git

What it does

Review Swarm is an agent skill from Dimillian/Skills. Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Subagents, Test coverage and Security review. It works with Git. The licence is MIT.

When your agent uses it

  • The user asks for a review swarm
  • Parallel review
  • Regression review
  • Security review

Example prompts

  • “/review-swarm”

Workflow steps

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

  1. Determine Scope and Intent
  2. Launch Four Read-Only Reviewers in Parallel
  3. Aggregate and Filter Findings
  4. Order the Output
  5. Recommend a Clear Path Forward

What it can do on your machine

Read from SKILL.md and the folder at commit 05ba982. 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

    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

Review Swarm loads about 1.6k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 940 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 Dimillian/Skills at commit 05ba982, republished under its MIT licence (© Dimillian). 940 words, ~1,638 tokens.

Download SKILL.mdSave it as .claude/skills/review-swarm/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
review-swarm
description
Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.

Review Swarm

Review a diff with four read-only sub-agents in parallel, then have the main agent filter, order, and summarize only the issues that matter. This skill is review-only: sub-agents do not edit files, and the main agent does not apply fixes as part of this workflow.

Step 1: Determine Scope and Intent

Prefer this scope order:

  1. Files or paths explicitly named by the user
  2. Current git changes
  3. An explicit branch, commit, or PR diff requested by the user
  4. Most recently modified tracked files, only if the user asked for a review and there is no clearer diff

If there is no clear review scope, stop and say so briefly.

When using git changes, choose the smallest correct diff command:

  • unstaged work: git diff
  • staged work: git diff --cached
  • mixed staged and unstaged work: review both
  • explicit branch or commit comparison: use exactly what the user requested

Before launching reviewers, read the closest local instructions and any relevant project docs for the touched area, such as:

  • AGENTS.md
  • repo workflow docs
  • architecture or contract docs for the touched module

Build a short intent packet for the reviewers:

  1. What behavior is meant to change
  2. What behavior should remain unchanged
  3. Any stated or inferred constraints, such as compatibility, rollout, security, or migration expectations

If the user did not state the intent clearly, infer it from the diff and say that the inference may be incomplete.

Step 2: Launch Four Read-Only Reviewers in Parallel

Launch four sub-agents when the scope is large enough for parallel review to help. For a tiny diff or one very small file, it is acceptable to review locally instead.

For every sub-agent:

  • give the same scope and the same intent packet
  • state that the sub-agent is read-only
  • do not let the sub-agent edit files, run apply_patch, stage changes, commit, or perform any other state-mutating action
  • ask for concise findings only
  • ask for: file and line or symbol, issue, why it matters, recommended follow-up, and confidence
  • tell the sub-agent to avoid nits, style preferences, and speculative concerns without concrete impact
  • tell the sub-agent to send findings back to the main agent only

Use these four review roles.

Sub-Agent 1: Intent and Regression Review

Review whether the diff matches the intended behavior change without introducing extra behavior drift.

Check for:

  1. Unintended behavior changes outside the stated scope
  2. Broken edge cases or fallback paths
  3. Contract drift between callers and callees
  4. Missing updates to adjacent flows that should change together

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Sub-Agent 2: Security and Privacy Review

Review the diff for security regressions, privacy risks, and trust-boundary mistakes.

Check for:

  1. Missing or weakened authn or authz checks
  2. Unsafe input handling, injection risks, or validation gaps
  3. Secret, token, or sensitive data exposure
  4. Risky defaults, permission expansion, or trust of unverified data

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Sub-Agent 3: Performance and Reliability Review

Review the diff for new cost, fragility, or operational risk.

Check for:

  1. Duplicate work, redundant I/O, or unnecessary recomputation
  2. Added work on startup, render, request, or other hot paths
  3. Leaks, missing cleanup, retry storms, or subscription drift
  4. Ordering, race, or failure-handling problems that make the change brittle

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Show full SKILL.md (349 more words)Show less
Sub-Agent 4: Contracts and Coverage Review

Review the diff for compatibility gaps and missing safety nets.

Check for:

  1. API, schema, type, config, or feature-flag mismatches
  2. Migration or backward-compatibility fallout
  3. Missing or weak tests for the changed behavior
  4. Missing logs, metrics, assertions, or error paths that make regressions harder to detect

This sub-agent is read-only. It must not edit files, apply patches, or make any other workspace changes.

Recommended sub-agent role: reviewer

Report only issues that materially affect correctness, security, privacy, reliability, compatibility, or confidence in the change. It is better to miss a nit than to bury the user in low-value noise.

Step 3: Aggregate and Filter Findings

The main agent owns synthesis. Treat sub-agent output as raw review input, not final output.

Merge findings across all four reviewers and filter aggressively:

  • drop duplicates
  • drop weak or speculative claims
  • drop issues that conflict with the stated intent
  • drop minor style or readability comments unless they hide a real bug or maintenance risk

Normalize surviving findings into this shape:

  1. File and line or nearest symbol
  2. Category: regression, security, reliability, or contracts
  3. Severity: high, medium, or low
  4. Why it matters
  5. Recommended fix or follow-up
  6. Confidence: high, medium, or low

If a reviewer may be correct but the intent is unclear, turn it into an open question instead of a finding.

Step 4: Order the Output

Present findings in this order:

  1. High-severity, high-confidence issues
  2. Medium-severity issues that are likely worth fixing before merge
  3. Lower-severity issues or follow-ups that can wait

Keep the review concise. Findings should be actionable and evidence-backed.

If there are no material issues, say that directly instead of manufacturing feedback.

Step 5: Recommend a Clear Path Forward

After the findings, give the user a short path forward:

  • what to fix before merge
  • what to improve if time permits
  • what can safely be left alone

When helpful, group the path forward into:

  • fix now
  • fix soon
  • optional follow-up

Do not implement fixes as part of this skill. The output is a read-only review plus a prioritized recommendation.

© Dimillian, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in review-swarm of Dimillian/Skills.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 05ba982

Compare with similar skills

Review Swarm 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.

Review Swarm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Swarm this skillDimillian/Skills4k—~1.6kAutomated safety check: PassMIT
Review Workpeterkrueck/Claude-Code-Development-Kit1.4k—~3.3kAutomated safety check: PassMIT
Review Swarmsickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassMIT
Review Codetobihagemann/turbo408—~3.3kAutomated safety check: PassMIT
Differential Security Reviewtrailofbits/skills7.5k—~1.8kAutomated safety check: NotesCC-BY-SA-4.0
Reviewgetsentry/sentry-react-native1.8k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Review Work

    peterkrueck/Claude-Code-Development-Kit

    Review uncommitted code changes using parallel Claude sub-agents (Bug Hunter, Rules Auditor, optional Architect).

    1.4k GitHub stars~3.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Review Swarm

    sickn33/agentic-awesome-skills

    Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test…

    47k GitHub starsUsed in 1 repo~1.9k tokens
    Agent WorkflowsAuto-check passed
  • Review Code

    tobihagemann/turbo

    Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps and low-value tests by running internal reviews and a peer review in…

    408 GitHub stars~3.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Official

    Reviews a pull request, commit or diff for security problems, using git history, caller counts and test coverage, and writes a markdown report.

    7.5k GitHub stars~1.8k tokensUpdated yesterday
    SecurityAuto-check: notes
  • Review

    getsentry/sentry-react-native

    Official

    Three-axis review of the branch diff — Standards (this repo's documented standards + public API/bridge surface), Spec (the originating Linear/GitHub issue or PR), and Correctness (runtime bugs + the…

    1.8k GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Review

    getsentry/sentry-dart

    Official

    Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat…

    873 GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from Dimillian/Skills

All 12 skills in this repo
  • macOS Spm App Packaging

    Dimillian/Skills

    Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project.

    4k GitHub starsUsed in 5 repos~1.2k tokens
    Auto-check passed
  • Analyze and optimize React component performance issues (slow renders, re-render thrash, laggy lists, expensive computations).

    4k GitHub starsUsed in 5 repos~1.2k tokens
    Auto-check passed
  • Swiftui View Refactor

    Dimillian/Skills

    Refactor and review SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage.

    4k GitHub starsUsed in 5 repos~2k tokens
    Auto-check passed
  • Swiftui UI Patterns

    Dimillian/Skills

    Best practices and example-driven guidance for building SwiftUI views and components, including navigation hierarchies, custom view modifiers, and responsive layouts with stacks and grids.

    4k GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed
  • Swift Concurrency Expert

    Dimillian/Skills

    Swift Concurrency review and remediation for Swift 6.2+. An agent skill from Dimillian/Skills.

    4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed
  • GitHub

    Dimillian/Skills

    Interact with GitHub using the gh CLI. An agent skill from Dimillian/Skills.

    4k GitHub stars~480 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Review Swarm

What does Review Swarm do?

Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test…. Review Swarm is an agent skill from Dimillian/Skills. Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps.

When should I use Review Swarm?

Review Swarm fits situations like: the user asks for a review swarm; parallel review; regression review; security review.

How do I install Review Swarm in Claude Code?

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

How do I install Review Swarm in Codex?

Run `npx skills add Dimillian/Skills --skill review-swarm -a codex`. Or copy the skill folder (review-swarm in Dimillian/Skills) into .agents/skills/review-swarm in your project. Codex loads it when a task matches its description.

Can I use Review Swarm 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 Dimillian/Skills --skill review-swarm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-swarm, .gemini/skills/review-swarm, .github/skills/review-swarm and .opencode/skills/review-swarm in your project.

What does Review Swarm need to run?

Going by SKILL.md and its folder, Review Swarm needs the command-line tools its instructions call (git).

Does Review Swarm 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 Review Swarm 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 Review Swarm use?

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

How many tokens does Review Swarm use?

About 1.6k tokens (SKILL.md is roughly 6.6k 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 Review Swarm?

Skills that share tags, products or a category with Review Swarm: Review Work (peterkrueck/Claude-Code-Development-Kit, 1.4k stars), Review Swarm (sickn33/agentic-awesome-skills, 47k stars), Review Code (tobihagemann/turbo, 408 stars) and Differential Security Review (trailofbits/skills, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Swarm?

Dimillian (a GitHub user) maintains it in Dimillian/Skills, which has 3,989 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on March 29, 2026.

Source: Dimillian/Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.