By thetribeio
Explore an existing codebase, produce a structured source code audit, and write functional documentation for the application.
A Claude Code plugin that helps clients understand an existing codebase through a four-phase workflow: exploration, structured audit, functional documentation, and optional PDF export.
When a client inherits, evaluates, or onboards onto an existing application, this plugin guides Claude through:
reportlab, using scripts/generate_audit_pdf.py.Phases 2–3 are defined entirely by this plugin’s references/ files. There is no dependency on separate code-review or documentation skills, and Claude Code does not chain skills automatically—those references are the source of truth.
| Phase | Requirement |
|---|---|
| 1–3 | None beyond the agent and repository access. |
| 4 (PDF) | Python 3.9+ and pip install reportlab. |
Fail fast before a long audit: from .agents/skills/codebase-audit/scripts/ run:
python check_audit_env.py --require-pdf
Use --require-pdf only when the user wants a PDF; if reportlab is missing, fix the environment before Phases 1–3.
Repo sizing (Phase 1): from the project under audit (repository root):
python /path/to/this/repo/.agents/skills/codebase-audit/scripts/repo_scope_hint.py
Then follow .agents/skills/codebase-audit/references/large-repository-strategy.md.
| Skill | Trigger phrases |
|---|---|
codebase-audit | "audit this codebase", "review the source code", "document this app", "give me an audit of the project" |
This repository includes .claude-plugin/plugin.json (plugin manifest) and .claude-plugin/marketplace.json (marketplace catalog with a single plugin entry).
codebase-audit plugin from the thetribe-plugins marketplace.If your Claude Code build only supports installing from a local path, clone this repo and use your product’s “install plugin from directory” flow pointing at the repository root (the folder that contains .claude-plugin/plugin.json).
This README does not use undocumented installers; if you publish elsewhere (e.g. community registries), document those steps in that channel.
Open or cd into the repository to audit, enable the plugin, then say for example:
"Audit this codebase and give me the functional documentation."
For markdown plus PDF, say so explicitly and ensure check_audit_env.py --require-pdf passes first.
Claude produces three shareable markdown sections — Codebase Map, Audit Report, and Functional Documentation — and can run scripts/generate_audit_pdf.py for Phase 4 when requested.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub thetribeio/agent-codebase-audit --plugin codebase-auditAudits a software codebase across 29 dimensions — security, privacy, accessibility, sector compliance (HIPAA/PCI/SOC 2/ISO 27001/FedRAMP/COPPA/FERPA/GLBA/EU AI Act/NIS2/DORA/Quebec Law 25), architecture, testing, dependencies, code reuse / consolidation, workaround / root-cause detection, performance, speed, DevOps, cost, engineering practice, UX, product gaps, frontend modernization, i18n, SEO, AI/ML, and product-type idioms. Produces structured docs under /docs/audits/ and files remediation tickets. Entry point: /audit.
Generate comprehensive analysis and documentation of entire codebase
Audit codebase documentation for accuracy, completeness, and freshness against actual code. Auto-fixes small discrepancies, reports structural changes. Companion to agent-ready.
Use this agent when you need to analyze a service or codebase component and create comprehensive documentation in CLAUDE.md files. This agent should be invoked after implementing new services, major refactoring, or when documentation needs updating to reflect the current codebase structure. Examples: <example>Context: The user has just implemented a new authentication service and wants to document it properly. user: 'I just finished implementing the auth service, can you document how it works?' assistant: 'I'll use the codebase-documenter agent to analyze the authentication service and create detailed documentation in CLAUDE.md' <commentary>Since the user has completed a service implementation and needs documentation, use the Task tool to launch the codebase-documenter agent to create comprehensive CLAUDE.md documentation.</commentary></example> <example>Context: The user wants to ensure a newly added API module is properly documented for the team. user: 'We need documentation for the new payment processing API I just added' assistant: 'Let me use the codebase-documenter agent to analyze the payment processing API and create proper documentation' <commentary>The user needs documentation for a new API module, so use the codebase-documenter agent to create CLAUDE.md files with setup instructions and architectural notes.</commentary></example>
Adversarial multi-agent pipeline for Claude Code. GAN-style loops where generators produce artifacts, discriminators validate them, and feedback drives convergence.
Audit and optimize Claude Code configurations with dynamic best-practice research