Review Codebase

Multi-phase deep codebase review with severity ratings and structured output. Covers architecture, security, code quality, and UX/accessibility in a single coordinated pass. Produces a prioritized findings table suitable for direct conversion to GitHub issues via the create-github-issues skill.

45 stars 4 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add pjt222/agent-almanac --skill review-codebase
Manual install
git clone --depth 1 https://github.com/pjt222/agent-almanac.git /tmp/agent-almanac
mkdir -p ~/.claude/skills
cp -r /tmp/agent-almanac/i18n/caveman-lite/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

Multi-phase deep codebase review producing severity-rated findings with fix-order recommendations. Unlike `review-pull-request` (scoped to a diff) or single-domain reviews (`security-audit-codebase`, `review-software-architecture`), this skill covers an entire project or subproject across all quality dimensions in one pass.

## When to Use

- Whole-project or subproject review (not PR-scoped)
- New codebase onboarding — building a mental model of what exists and what needs attention
- Periodic health checks after sustained development
- Pre-release quality gate across architecture, security, code quality, and UX
- When the output should feed directly into issue creation or sprint planning

## Inputs

- **Required**: `target_path` — root directory of the codebase or subproject to review
- **Optional**:
  - `scope` — which phases to run: `full` (default), `security`, `architecture`, `quality`, `ux`
  - `output_format` — `findings` (table only), `report` (narrative), `both` (default)
  - `severity_threshold` — minimum severity to include: `LOW` (default), `MEDIUM`, `HIGH`, `CRITICAL`

## Procedure

### Step 1: Census

Inventory the codebase to establish scope and identify review targets.

1. Count files by language/type: `find target_path -type f | sort by extension`
2. Measure total line counts per language
3. Identify test directories and estimate test coverage (files with tests vs files without)
Read the full skill on GitHub

Details

Skill name
review-codebase
Path
i18n/caveman-lite/skills/review-codebase/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Review Codebase skill do?

Multi-phase deep codebase review with severity ratings and structured output. Covers architecture, security, code quality, and UX/accessibility in a single coordinated pass. Produces a prioritized findings table suitable for direct conversion to GitHub issues via the create-github-issues skill.

How do I install the Review Codebase skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add pjt222/agent-almanac --skill review-codebase. 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 pjt222/agent-almanac, which has 45 GitHub stars and 4 forks, and is included in 1 curated skill list.

Related skills

Adapt Architecture

45

pjt222/agent-almanac

Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers transformation planning, parallel running, progressive cutover, rollback design, and post-metamorphosis stabilization for system architecture evolution. Use when assess-form has classified the system as READY for transformation, when migrating from monolith to microservices, when replacing a core subsystem while dependents continue operating, or when any architectural change must be gradual rather than big-bang.

Software DevelopmentIn 1 list

Adaptic

45

pjt222/agent-almanac

Master skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates meditate, expand-awareness, observe, awareness, integrate-gestalt, and express-insight into a coherent process that produces unified understanding rather than sequential compromise. Use when a problem genuinely spans 3+ domains and the interactions between domains matter more than depth in any one, when sequential analysis feels like compromise rather than integration, or before major architectural decisions affecting multiple stakeholders.

OtherIn 1 list

Add Puzzle Type

45

pjt222/agent-almanac

Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires it into the unified pipeline (generation, positioning, rendering, adjacency), adds ggpuzzle geom/stat layers, updates DESCRIPTION and config.yml, extends the Shiny app, and creates a comprehensive test suite. Use when adding a completely new puzzle type to the package or following the 10-point integration checklist to ensure nothing is missed end-to-end.

Testing & QAIn 1 list

Review Software Architecture

45

pjt222/agent-almanac

Review software architecture for coupling, cohesion, SOLID principles, API design, scalability, and technical debt. Covers system-level evaluation, architecture decision record review, and improvement recommendations. Use when evaluating a proposed architecture before implementation, assessing an existing system for scalability or security, reviewing ADRs, performing a technical debt assessment, or evaluating readiness for significant scale-up.

Software DevelopmentIn 1 list

Remote Viewing

45

pjt222/agent-almanac

AI intuitive exploration for approaching unknown codebases, problems, or systems without preconceptions. Adapts the Coordinate Remote Viewing protocol to AI investigation: cooldown (clear assumptions), staged data gathering (raw signals → dimensional → analytical), AOL management (separating observations from premature labels), and structured review. Use when investigating an unfamiliar codebase with unknown architecture, debugging a problem where premature hypotheses could mislead, exploring a domain with limited context, or when previous attempts have been led astray by assumptions and "begi

Software DevelopmentIn 1 list

Scaffold CLI Command

45

pjt222/agent-almanac

Scaffold a new CLI command using Commander.js with options, action handler, three output modes (human-readable, quiet, JSON), and optional ceremony variant. Covers naming, option design, shared context patterns, error handling, and integration testing. Use to add a command to an existing Commander.js CLI, design a new CLI tool from scratch, or standardize command structure across a multi-command CLI.

Software DevelopmentIn 1 list

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