code-review

A guide for running a code review with several specialized reviewers. The review can cover the whole codebase or search the whole tree for one specific recurring code problem.

In plain words
What is it for?
Use it for architecture, security, testing, consistency, duplication, and layering reviews, or for a targeted scan of one known code pattern.
Why use it?
It broadens review beyond one person’s perspective and helps find repeated issues across files. The focused mode can act as a quick check during a ticket.

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/postindustria-tech/agentic-toolkit/code-review
Any agent
npx skills add postindustria-tech/agentic-toolkit --skill code-review
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Made for: Claude Code, Codex.

Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,593 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 $0.00139 $0.03593
Opus 5 $0.00069 $0.01796
Sonnet 5 $0.00028 $0.00719
Haiku 4.5 $0.00014 $0.00359

Measured yesterday against content hash a5f5dc650452, 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_targeted_wiring.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/dev-practices/skills/code-review/SKILL.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Code Review

Two modes

Mode Invocation Scope Agents Output When
FULL (default) code-review [scope] whole codebase, all dimensions 5-7 dimensional reviewers per-agent .md + synthesis.md periodic / exhaustive audit
TARGETED code-review --targeted "<disease-spec>" [ticket-id] ONE disease pattern, whole tree 3 disease-scoped lenses + optional opus per-lens .md + a one-page disposition table fast (<5 min) in-loop ticket phase-gate

If --targeted is the first argument, jump to Targeted Mode below. Otherwise run the FULL protocol (the rest of this document).

The two modes share one purpose contract but NOT scope: the targeted mode is fast and disease-specific; the full audit is periodic and exhaustive. Do not collapse them.


Targeted Mode (--targeted "<disease-spec>" [ticket-id])

A single-disease, whole-tree scan meant to run as a phase-gate INSIDE a ticket (the molecule's codebase-scan / sweep-verify atoms invoke it). It answers "does this disease appear anywhere else?" and emits a disposition table, NOT a 41-finding catalog.

When to use it vs. a plain grep: the multi-agent fan-out earns its cost for semantic diseases -- logic re-implemented under different names, a helper bypassed by hand-rolled variants -- where one grep cannot find every variant. For a purely syntactic disease (one exact literal, a single regex-able form), a single-executor grep in the codebase-scan atom is sufficient; do NOT fan out for those.

Protocol

  1. Load team + parse args. ToolSearch: "select:TeamCreate", "select:TaskCreate", "select:SendMessage". First arg after --targeted is the one-line DISEASE-PATTERN SPEC; the next (optional) is the ticket-id.

  2. Output dir keyed to the ticket (so the artifact is discoverable and the gate can require it):

    TICKET_ID="<ticket-id-or-fallback>"     # e.g. neograph-djpi
    REVIEW_DIR=".claude/code-review/${TICKET_ID:-$(date +%d%m%y_%H%M)}"
    mkdir -p "$REVIEW_DIR"
    

Read the full file on GitHub · 379 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 379 lines · 139 tokens per session scan A a5f5dc650452

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 3,593 once invoked, about $0.0007 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

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

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