Agent skill

Code Review

by 6BNBN in 6BNBN/FlowPilot

A skill your agent uses when the user asks to review a pull request or diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings.

MITAuto-check passedDevelopment

Install Code Review

skills CLI
$ npx skills add 6BNBN/FlowPilot --skill code-review -a claude-code

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

GitHub CLI
$ gh skill install 6BNBN/FlowPilot code-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/6BNBN/FlowPilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'兼容codex@cursor一键安装技能/codex一键安装技能/纯手动安装/skills/code-review' .claude/skills/code-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
code-review
GitHub stars
134
Token cost
~624 tokens
SKILL.md length
327 words
Files
2 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user asks to review a pull request or diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings.

  • Works in 7 steps: Eligibility check → Collect local guidance → Summarize the change → …
  • The user asks to review a pull request
  • SKILL.md covers Source of truth, Review Workflow, Comment Format and Review Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Review is an agent skill from 6BNBN/FlowPilot. Use when the user asks to review a pull request or diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings.

Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/code-review-command.md`).

It sits in Development, covering Code review and Pull requests. It works with GitHub. The repository describes itself as: 一句需求,自动拆任务、并行多代理写码、断点恢复、验证收尾。FlowPilot 让 Claude Code / Codex / Cursor / snow-cli 进入真正的自动开发流程。 The licence is MIT.

When your agent uses it

  • The user asks to review a pull request
  • Diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings

Example prompts

  • “/code-review”

Workflow steps

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

  1. Eligibility check
  2. Collect local guidance
  3. Summarize the change
  4. Run parallel review passes
  5. Confidence-check findings
  6. Filter for signal
  7. Comment or report

What it can do on your machine

Read from SKILL.md and the folder at commit 57b1d49. 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.

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

  • Network

    No URLs in SKILL.md.

    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 Review loads about 624 tokens when it runs, and up to ~832 if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 327 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~624
With references · SKILL.md plus every file in references/, read only if the agent opens them
~832

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 6BNBN/FlowPilot at commit 57b1d49, republished under its MIT licence (© 6BNBN). 327 words, ~624 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
code-review
description
Use when the user asks to review a pull request or diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings.

Codex-Native PR Code Review

Use this workflow to review a pull request or diff with gh when available. Keep findings high-signal, actionable, and grounded in the actual change.

Source of truth

eferences/code-review-command.md

Review Workflow

  1. Eligibility check

    • Confirm the PR is still open and ready for review.
    • Skip review if it is clearly out of scope, already handled, or obviously trivial.
  2. Collect local guidance

    • Identify the relevant AGENTS.md files for the touched paths.
    • Treat those files as code-review guidance when applicable.
  3. Summarize the change

    • Use one fast subagent to summarize the PR and changed areas.
  4. Run parallel review passes

    • Launch independent review subagents with different lenses:
      • conventions and AGENTS.md compliance
      • correctness and bug risk
      • history and git blame context
      • prior PR or discussion context when relevant
      • comments or invariants near the changed code
  5. Confidence-check findings

    • Re-check each finding with a separate pass before surfacing it.
    • Drop weak or speculative issues.
  6. Filter for signal

    • Ignore trivial lint, formatting, or typecheck issues that CI should catch separately.
    • Ignore pre-existing issues unless the current PR makes them worse.
    • Keep only the issues that matter to a senior engineer reviewing this change.
  7. Comment or report

    • If the user asked for a GitHub comment, use gh to post it.
    • Otherwise, present the findings directly in the session.

Comment Format

Use this structure for final findings:

`markdown

Code review

Found 2 issues:

  1. Brief description of issue

    • Why it matters
    • Evidence: file path or URL with full commit SHA when linking to GitHub
  2. Brief description of issue

    • Why it matters
    • Evidence: file path or URL with full commit SHA when linking to GitHub `

If no issues remain after filtering:

`markdown

Code review

No actionable issues found. Checked for correctness, local guidance, and regression risk. `

Review Rules

  • Use gh for GitHub operations when available.
  • Prefer concrete evidence over speculation.
  • Keep comments brief and free of signatures or emojis.
  • Cite paths or links precisely when pointing to code.

© 6BNBN, 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 (references) in 兼容codex@cursor一键安装技能/codex一键安装技能/纯手动安装/skills/code-review of 6BNBN/FlowPilot.

  • SKILL.md
  • references/code-review-command.md

Open the folder on GitHubat commit 57b1d49

Compare with similar skills

Code 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.

Code Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Review this skill6BNBN/FlowPilot134—~624Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT
PR Review State Fetchprisma/orm48k—~767Automated safety check: PassApache-2.0
Fastlane Pull Request Reviewfastlane/fastlane42k—~550Automated safety check: PassMIT

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
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Official

    Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.

    48k GitHub stars~767 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately.

    42k GitHub stars~550 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Reviews open pull requests in the daisyUI repository using read-only GitHub data and isolated base-versus-PR checks, then writes a merge verdict report.

    43k GitHub stars~766 tokensUpdated 8 days ago
    DevelopmentAuto-check passed

More from 6BNBN/FlowPilot

All 21 skills in this repo
  • Playwright

    6BNBN/FlowPilot

    A skill your agent uses when the task requires automating a real browser from the terminal in Cursor, including navigation, form filling, snapshots, screenshots, data extraction, and UI-flow…

    134 GitHub stars~1k tokensUpdated 6 mo ago
    Auto-check passed
  • A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

    134 GitHub starsUsed in 1 repo~301 tokens
    Auto-check passed
  • Feature Dev

    6BNBN/FlowPilot

    A skill your agent uses when the user asks to build a new feature and wants a structured Codex CLI workflow with discovery, clarifying questions, architecture comparison, implementation, and review.

    134 GitHub stars~823 tokensUpdated 6 mo ago
    Auto-check passed
  • Writing Skills

    6BNBN/FlowPilot

    A skill your agent uses when creating, editing, or validating Cursor custom skills, especially when deciding where they should live, how they should be named, and how to describe when they apply.

    134 GitHub stars~322 tokensUpdated 6 mo ago
    Auto-check passed
  • Code Review

    6BNBN/FlowPilot

    A skill your agent uses when the user asks for a code review of local files, a workspace, a branch diff, or a pull request.

    134 GitHub stars~465 tokensUpdated 6 mo ago
    Auto-check passed
  • Feature Dev

    6BNBN/FlowPilot

    A skill your agent uses when building a new feature or substantial behavior change in Cursor and the user wants a structured workflow from discovery through implementation and review.

    134 GitHub stars~439 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Categories

Questions about Code Review

What does Code Review do?

A skill your agent uses when the user asks to review a pull request or diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings. Code Review is an agent skill from 6BNBN/FlowPilot. Use when the user asks to review a pull request or diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings.

When should I use Code Review?

Code Review fits situations like: the user asks to review a pull request; diff with a structured Codex CLI workflow using parallel review passes and filtered actionable findings.

How do I install Code Review in Claude Code?

Run `npx skills add 6BNBN/FlowPilot --skill code-review -a claude-code`. Or copy the skill folder (兼容codex@cursor一键安装技能/codex一键安装技能/纯手动安装/skills/code-review in 6BNBN/FlowPilot) into .claude/skills/code-review in your project. Claude Code loads it when a task matches its description.

How do I install Code Review in Codex?

Run `npx skills add 6BNBN/FlowPilot --skill code-review -a codex`. Or copy the skill folder (兼容codex@cursor一键安装技能/codex一键安装技能/纯手动安装/skills/code-review in 6BNBN/FlowPilot) into .agents/skills/code-review in your project. Codex loads it when a task matches its description.

Can I use Code 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 6BNBN/FlowPilot --skill code-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/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.

What does Code Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Review is instructions for the agent only.

Does Code Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Code 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 Code Review use?

Code Review 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 Code Review use?

About 624 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 208 tokens, read only when the agent opens those files.

What are the alternatives to Code Review?

Skills that share tags, products or a category with Code Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), GitHub Review Iteration (prisma/orm, 48k stars), PR Finalize Review (microsoft/garnet, 12k stars) and PR Review State Fetch (prisma/orm, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

6BNBN (a GitHub user) maintains it in 6BNBN/FlowPilot, which has 134 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on March 13, 2026.

Source: 6BNBN/FlowPilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.