Review Codebase

Use to run a whole-system adversarial audit of the current repo across three lenses at once — codebase (defects, incoherences, affordance gaps), docs (drift, structure, coverage), and process (end-to-end workflow dead ends). Dispatches three fresh Claude subagents in parallel, each writing a ranked findings report to docs/audits/, then offers an optional fix pass on CRITICAL findings. Triggers on: review codebase, audit codebase, audit this repo, adversarial audit, codebase audit, docs audit, process audit, fable audit, three reviews, full audit, whole-system review, find everything wrong.

5 starsSoftware Development Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add adelrioj/claude-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add adelrioj/claude-skills --skill review-codebase
Manual install
git clone --depth 1 https://github.com/adelrioj/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/review-codebase ~/.claude/skills/review-codebase

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Review Codebase — Three-Lens Adversarial Audit

Fires the three **Fable adversarial audits** — codebase, docs, and process — against the
current repository, all at once. It automates the launcher from
[this gist](https://gist.github.com/diegomarino/04970a2b8d9cc419de3ba05b9a03db5a): instead
of fetching the prompts into `.prompts/` and pasting a `/goal` per prompt, the three prompts
are **embedded as templates** and each is dispatched to its own fresh-context subagent.

**Where it sits in the review family:**
- `/code-review`, `/review-pr` — line-level *correctness* on a diff.
- `/spec-review-codex` / `-local` — harden the *spec, before* code exists.
- `/architect-review-pr` — *completeness & wiring* of one finished feature (one subagent).
- **`/review-codebase`** — *whole-system* audit across three lenses (three subagents). This skill.

**Why fresh subagents (the adversarial mechanism).** Each audit re-derives its findings from
the code alone, with no memory of how the system was built — the same independence rationale
as `/architect-review-pr`. Three run in **parallel**, isolated, so each full-repo audit's raw
output stays out of the main loop. No external CLI — subagents
are Claude `Agent`s, so the skill installs anywhere.

**Report + optional fix.** Each audit is report-first: it writes a ranked, ID'd findings report
to `docs/audits/` and returns only a short summary. After the three land, the skill *offers* a
Read the full skill on GitHub

Details

Skill name
review-codebase
Path
skills/review-codebase/SKILL.md
Repo updated
24 August 2026

FAQ

What does the Review Codebase skill do?

Use to run a whole-system adversarial audit of the current repo across three lenses at once — codebase (defects, incoherences, affordance gaps), docs (drift, structure, coverage), and process (end-to-end workflow dead ends). Dispatches three fresh Claude subagents in parallel, each writing a ranked findings report to docs/audits/, then offers an optional fix pass on CRITICAL findings. Triggers on: review codebase, audit codebase, audit this repo, adversarial audit, codebase audit, docs audit, process audit, fable audit, three reviews, full audit, whole-system review, find everything wrong.

How do I install the Review Codebase skill?

Claude Code plugin: /plugin marketplace add adelrioj/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Review Codebase popular?

It lives in adelrioj/claude-skills, which has 5 GitHub stars and 0 forks.

Related skills

Architect Review PR

5

adelrioj/claude-skills

Use after a feature is built — e.g. the final step of a ship-it run, right after review-pr — to check it is actually complete and wired, not just line-correct. Dispatches a fresh-context Claude subagent that traces the whole repo to hunt completeness and integration gaps in the branch's changes, reports ranked, evidence-backed findings, then fixes the CRITICAL ones and verifies with a fresh re-review (capped at 3 passes; pass report-only to skip fixing). Triggers on: architect review, architecture review, completeness review, wiring review, is this wired, did we finish this, find the gaps, inc

Git & Code Review

Blind Spot

5

adelrioj/claude-skills

Use BEFORE starting work on a task to surface the unknown-unknowns you're about to walk into but can't see. Dispatches a fresh-context Claude subagent that hunts what you don't know you don't know about the codebase, the domain, and the decisions ahead, calibrated to your stated experience, then reports ranked, evidence-backed findings and fixes nothing. Triggers on: blind spot pass, blindspot, unknown unknowns, what don't I know, what am I missing, help me prompt better, I know nothing about, teach me my unknowns, before I start, de-risk this task, surface my blind spots.

AI, LLMs & Agents

Claude Md Slim

5

adelrioj/claude-skills

Use when CLAUDE.md has grown bloated and is taxing every session's context — the inverse of claude-md-improver. Triages each block into session-invariant rules (stay always-on) vs feature/subsystem detail (page out to docs/ behind a plain-path pointer), moving — never deleting — the detail so nothing is lost and the always-on token bill drops. Triggers on: slim claude.md, minimal claude.md, claude.md is bloated, shrink claude.md, split claude.md, make claude.md minimal, page out claude.md, claude.md too long, reduce project memory, point claude.md to docs, trim claude md.

AI, LLMs & Agents

Spec Review Codex

5

adelrioj/claude-skills

Use when a brainstorming design spec has been written and needs adversarial review before implementation planning, using OpenAI Codex as the independent reviewer. Requires the codex CLI. Triggers on: spec review codex, codex spec review, review spec with codex, codex review, review spec, spec review.

Software Development

Plan to Dex

5

adelrioj/claude-skills

Use when running an already-hardened Superpowers implementation plan through the dex orchestrator (codex backend). Triggers on: convert plan to dex, plan to dex, dex from plan, run plan with dex, plan-to-dex.

Software Development

Spec Review Local

5

adelrioj/claude-skills

Use when a brainstorming design spec has been written and needs adversarial review before implementation planning, using a local model served by LMStudio (via the pi CLI) as the independent reviewer. Works offline — no hosted API needed. Triggers on: spec review local, local spec review, review spec locally, lmstudio review, review spec, spec review.

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.