code-review

A code-review coordinator that identifies a project's programming language and structure, then applies the relevant review checklist. It can use an existing project map or make a quick one.

In plain words
What is it for?
Use it to review Go, TypeScript, Python, PHP, or architecture-focused changes, with a general checklist when no specific review applies.
Why use it?
It removes the need to choose the right review method manually and helps reviewers start with the project's actual structure.

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

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,014 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 $0.00080 $0.01014
Opus 5 $0.00040 $0.00507
Sonnet 5 $0.00016 $0.00203
Haiku 4.5 $0.00008 $0.00101

Measured 2d ago against content hash 8acfb24024ed, 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 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/development/code-review/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill

Entry point for all code reviews. Detects context and routes to the right specialized skill.

Step 0 — Load Project Map

Check for .agentic/project-map.md:

  • If present: read it. Use the layer structure, key modules, and conventions it defines as the foundation for all findings. Skip redundant filesystem exploration.
  • If absent: run lightweight auto-discovery:
    • Detect language from go.mod, package.json, tsconfig.json, pyproject.toml, composer.json
    • List top-level directories to understand project structure
    • Read the entry point file (e.g. main.go, src/index.ts, app/main.py) for ~20 lines of context
    • Suggest running the project-map skill after this review to avoid discovery overhead next time

Step 1 — Detect Language and Architecture

Language detection (inspect file extensions + manifest files):

Signal Language
go.mod present Go
tsconfig.json or package.json with TypeScript devDep TypeScript
pyproject.toml or setup.py Python
composer.json PHP

Architecture detection (inspect directory names and import patterns):

Signal Architecture
domain/, application/, infrastructure/, ports/ directories Hexagonal / Clean
Aggregate root classes, domain events, value objects DDD
command/ + query/ directories, command/query handler classes CQRS
Multiple independent services each with their own data store Microservices

Step 2 — Route to Specialized Skill(s)

Load and apply the appropriate skill(s):

Detected Skill to apply
Go code-review-go
TypeScript / JavaScript code-review-typescript
Python code-review-python
PHP code-review-php
Hexagonal / DDD / CQRS / Microservices markers code-review-architecture (in addition to language skill)
Mixed or unrecognized Apply generic checklist.md only

Multiple skills can be active simultaneously (e.g. Go + Architecture for a Go hexagonal service).

Read the full file on GitHub · 124 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. 2d ago First seen · 124 lines · 80 tokens per session scan A 8acfb24024ed

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 1,014 once invoked, about $0.0004 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.