code-review

code-review is a skill for Claude Code, Codex from IgorWarzocha/howaboua-pi-stuff. It costs 13 tokens per session (956 once invoked), scanned A, original, MIT.

A review guide for maintained-code changes that checks both whether the requested behavior is correct and whether the codebase remains coherent. It covers the full change set, related callers, contracts, tests, configuration, and runtime behavior.

In plain words
What is it for?
Use it to review pull requests, trace changes from their entry point to their effects, check that tests exercise real production paths, and identify missing or unrequested behavior.
Why use it?
It helps prevent reviews that focus only on the latest commit or on code style while missing incomplete requirements, regressions, or broken ownership and lifecycle rules.

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/igorwarzocha/howaboua-pi-stuff/code-review
Any agent
npx skills add IgorWarzocha/howaboua-pi-stuff --skill code-review
Clone the repo
git clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuff

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/code-review.svg)](https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/code-review)
Your own site
<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/code-review"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 956 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 $0.00013 $0.00956
Opus 5 $0.00006 $0.00478
Sonnet 5 $0.00003 $0.00191
Haiku 4.5 $0.00001 $0.00096

Measured 5d ago against content hash 0c8159f75fff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 5d 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.

packages/pi-skill-code/skills/code-review/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load an applicable codebase hygiene skill and apply it throughout.

Judge two concerns independently:

  • Intent and correctness: the requested behavior is complete, with no unrequested behavior or regression.
  • Codebase hygiene: ownership, contracts, execution, lifecycle, tests, and file boundaries remain coherent.

Never let one concern excuse failure in the other. Treat implementation, tests, comments, types, and documentation produced from the same premise as one evidence source. Agreement within the patch is not independent proof.

1. Establish scope

  1. Resolve the intended base. Inspect the full diff and commit range, not only the last commit.
  2. Read the request, acceptance criteria, complete changed files, affected callers, public contracts, tests, configuration, and runtime registration.
  3. Trace changed behavior from a real entry point to its result or effect. Confirm tests reach the production path.
  4. Record claimed behavior, missing or partial requirements, unrequested scope, and behavior that must remain stable.
  5. Separate observed requirements, compatibility assumptions, and reviewer inference. Ask only when the distinction changes the verdict.

2. Establish evidence

Prefer:

  1. explicit acceptance criteria and confirmed product decisions
  2. public compatibility contracts, persisted formats, protocols, and observed external behavior
  3. stable prior behavior when compatibility is required
  4. independent callers or implementations with matching semantics
  5. tests, comments, names, and implementation structure

Identify the one or two facts the change relies on for safety, including facts beyond direct callers. Prove each with source evidence, an unreachable failure path, an executable check, or the running artifact. Mark unproved claims as unproved.

3. Challenge each material claim

Choose the cheapest decisive falsifier:

  • Regression: reproduce the failure or exact old path. Confirm the cause is removed rather than hidden by a guard, retry, fallback, or catch.
  • Boundary logic: probe supported transitions around empty, singleton, first, last, missing, duplicate, zero, limits, and ordering.
  • Refactor or optimization: compare observable behavior before and after on representative supported inputs. Judge differences against the contract.
  • State or lifecycle: probe illegal order, repetition, partial failure, cancellation, retry exhaustion, cleanup, shutdown, and ownership transfer.
  • Serialization or compatibility: round-trip real supported data. Inspect old readers, writers, stored data, and version boundaries.
  • Test: name a plausible wrong implementation the test rejects. For regressions, demonstrate fail-before and pass-after when practical. Registration, rendering, symbol existence, type validity, and mock choreography are not evidence.
  • External integration: verify the project-owned boundary. Use controlled real-provider evidence when compatibility itself matters. A hand-built double cannot prove an external API.

Read the full file on GitHub · 79 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. 5d ago First seen · 79 lines · 13 tokens per session scan A 0c8159f75fff

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (346 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 956 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 2026-08-30.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens