review

A review command that sends a plan or pull request to an independent senior-engineer reviewer and repeats the review until it is approved. A pull request is a proposed set of code changes for review before merging.

In plain words
What is it for?
Use it to review the active plan, a file containing a specific plan, the current branch's changes, or a numbered pull request. It can also explicitly approve the work and skip further review rounds.
Why use it?
It adds an independent check for logic errors, design problems, missing tests, security issues, and performance concerns before changes are accepted.

Skill for Claude CodeCodex

Part of the para plugin — 11 skills, 1 hook shipped together

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.

agentmods
npx agentmods add skills/brian-lai/para-programming-plugin/review
Any agent
npx skills add brian-lai/para-programming-plugin --skill review
Clone the repo
git clone --depth 1 https://github.com/brian-lai/para-programming-plugin

Made for: Claude Code, Codex.

Or install para, the plugin that ships this one along with the rest of its 11 skills, 1 hook.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.01243
Opus 5 $0.00010 $0.00622
Sonnet 5 $0.00004 $0.00249
Haiku 4.5 $0.00002 $0.00124

Measured 2d ago against content hash 9f570e6e67ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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 2d 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.

skills/review/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spawn an independent subagent with a Staff+ FAANG engineer persona to review a plan or PR. The review loops until the reviewer explicitly approves.

Usage

/para:review --plan                    # Review the active plan
/para:review --plan=path/to/plan.md    # Review a specific plan file
/para:review --pr                      # Review the current branch's changes as a PR
/para:review --pr=123                  # Review a specific PR number
/para:review --approve                 # Override: skip remaining review rounds and approve

Staff+ FAANG Engineer Reviewer Persona

The subagent receives the following persona instructions:

You are a Staff+ engineer at a FAANG company reviewing this work. You have high standards for:

  • Architecture: Clean boundaries, appropriate abstractions, no over-engineering
  • Correctness: Logic errors, race conditions, edge cases, error handling
  • Testing: TDD adherence, test coverage, test quality (not just quantity)
  • Maintainability: Code clarity, naming, documentation where needed
  • Security: Input validation, injection risks, secrets handling
  • Performance: Obvious inefficiencies, N+1 queries, unnecessary allocations

Be specific and actionable in feedback. Reference exact file paths and line numbers. Categorize each issue as: MUST FIX (blocks approval) | SHOULD FIX (strong recommendation) | NIT (optional improvement). When there are no remaining MUST FIX issues, explicitly state: "APPROVED — ready to proceed."

Plan Review Process

When --plan is specified:

  1. Identify the plan — read from context/context.md active plan (or use the path provided).

  2. Spawn a subagent with the Staff+ persona. The subagent reads the full plan (and all sub-plans for phased plans) and checks:

    • Are all interface boundaries identified with contracts?
    • Is TDD ordering correct (tests before implementation)?
    • Are checklist items atomic and commit-message-ready?
    • Is graceful degradation addressed for external dependencies?
    • Is scope appropriate (not over-engineered)?
    • Are architecture decisions documented with rationale?
    • Are test annotations concrete (function signatures, not vague descriptions)?

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 21 tokens per session scan A 9f570e6e67ca

Subscribe to this mod's changes

review is a skill published in the GitHub repository brian-lai/para-programming-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 1,243 once invoked, about $0.0001 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens