review-codebase

A whole-codebase review process that divides a project into documented features and assigns each feature to a code-review agent.

In plain words
What is it for?
Reviewing all features, selected areas, stale features, directories, or only high-severity issues, then combining the findings into one report.
Why use it?
It helps find bugs, security issues, performance problems, and other quality concerns across a large project without changing it by default.

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/jakubsuplicki/codument/review-codebase
Any agent
npx skills add jakubsuplicki/codument --skill review-codebase
Clone the repo
git clone --depth 1 https://github.com/jakubsuplicki/codument

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,078 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 $0.00093 $0.01078
Opus 5 $0.00046 $0.00539
Sonnet 5 $0.00019 $0.00216
Haiku 4.5 $0.00009 $0.00108

Measured 3d ago against content hash eb23604440b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-codebase 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/review-codebase/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Review

You are the orchestrator for a full codebase review. Your job is to divide the codebase into reviewable chunks (using the documentation registry's feature boundaries), delegate each chunk to a code-reviewer agent, and compile the results into a unified report.

How It Works

Step 1: Read the registry

Read docs/.registry.json to get the feature map. Each registry entry defines a feature with its source files — these are your review units.

If no registry exists, tell the user to run codument scan first.

Step 2: Determine review scope

By default, review all features. The user may narrow scope:

  • Specific features: "review auth and payments"
  • By status: "review stale features only"
  • By directory: "review everything under src/api/"
  • By severity filter: "only critical and high issues"

If the user doesn't specify, review everything.

Step 3: Spawn code-reviewer agents

For each feature in scope, spawn a code-reviewer agent with specific instructions:

Review the "{feature-name}" feature.
Doc: {doc path from registry}
Source files to review:
{list each file from the registry entry's sources array}

Focus areas: correctness, security, performance, error handling, type safety.
Report findings by severity: Critical, High, Medium, Low.
Include a Positives section for what's done well.
{any user-specified focus or constraints}

Batching:

  • Small projects (< 6 features): spawn all agents in parallel
  • Larger projects: batch 3-5 agents at a time to avoid overwhelming the system

Important: Be specific in agent instructions. Include the exact file paths. Vague instructions produce vague reviews.

Step 4: Compile the report

After all agents complete, compile findings into a unified report:

# Codebase Review Report

**Date**: YYYY-MM-DD
**Features reviewed**: N
**Total findings**: N (X critical, Y high, Z medium, W low)

## Critical Issues
[all critical findings across features, grouped by feature]

## High Priority
[all high findings across features, grouped by feature]

## Medium Priority
[all medium findings, grouped by feature]

## Low Priority
[summary count only — detail available per-feature]

## Highlights
[notable positives across the codebase]

## Recommended Priorities
[ordered list: what to fix first based on severity and blast radius]

Read the full file on GitHub · 126 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. 3d ago First seen · 126 lines · 93 tokens per session scan A eb23604440b8

Subscribe to this mod's changes

review-codebase is a skill published in the GitHub repository jakubsuplicki/codument (47 stars, last pushed 12d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,078 once invoked, about $0.0005 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.