review-code

A rigorous review process for code changes on the current branch, checking correctness, security, speed, project rules, and less obvious edge cases.

In plain words
What is it for?
Use it to review local changes, check a branch, or assess code before release. It examines project instructions as well as possible bugs, security risks, performance issues, and missing documentation.
Why use it?
It helps find problems before code is merged or deployed, including issues that ordinary syntax checks may miss. The review is separated from the implementation context to encourage independent criticism.

Skill for Claude CodeCodex

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/p2ergmbh/agentic-coding/review-code
Any agent
npx skills add P2ERGmbH/agentic-coding --skill review-code
Clone the repo
git clone --depth 1 https://github.com/P2ERGmbH/agentic-coding

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,888 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 $0.00034 $0.01888
Opus 5 $0.00017 $0.00944
Sonnet 5 $0.00007 $0.00378
Haiku 4.5 $0.00003 $0.00189

Measured 2d ago against content hash da6010d8fa83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-code 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.

.agents/skills/review-code/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Uncompromising Local Code Review Workflow (Hyper-Intense Edition)

This workflow defines an exceptionally rigorous, high-standard local code review. You are not just checking syntax; you are acting as an uncompromising senior architect, performance engineer, and security gatekeeper ensuring that the local branch changes remain pristine, elegant, and perfectly compliant with all project mandates.

Subagent Isolation (Mandatory)

You MUST run this entire review process inside an isolated generalist or research subagent. This decouples the review context from the implementation context, guaranteeing an unbiased, critical, and hyper-meticulous evaluation of all local/branch changes.

Persona & Standard

Your review persona is constructive, precise, and absolutely uncompromising. Your adherence to project-specific rules (GEMINI.md, docs/rules/) is absolute. Do not overlook minor stylistic deviations, missing documentations, or potential edge-case errors. Treat every local review as if it is blocking a multi-million-user production deployment.

Trigger

Use this workflow whenever requested to "do a code review", "review local changes", "check my code", or when executing local reviews before creating or finalizing a Pull Request.


Phase 1: Meticulous Context Gathering

  1. Read Mandates (CRITICAL FIRST STEP): Before running any analysis, you MUST explicitly read the current contents of the core guidelines to load them fully into active context:
    • GEMINI.md (Absolute authority)
    • docs/rules/general.md
    • docs/rules/next.md (if UI or Next.js files are changed)
    • docs/rules/testing.md (if tests are modified or added)
  2. Identify Full Scope:
    • Find the base branch (usually main) and gather the complete list of changed/untracked files.
    • Retrieve the full content (not just diff snippets) of all changed, added, or refactored files to understand the architectural context of the edits.
  3. Cross-File Regression Scan:
    • Examine related components or import targets of the changed files to ensure changes do not break downstream layers.

Read the full file on GitHub · 116 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 · 116 lines · 34 tokens per session scan A da6010d8fa83

Subscribe to this mod's changes

review-code is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 1,888 once invoked, about $0.0002 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens