claude

audit-code

Read-only codebase audit suite. A master orchestrator (audit-code-master) fans out parallel sub-agents across focused dimension skills (security, correctness, performance, quality, architecture, dependencies, testing, social-preview) and renders a styled HTML report; each dimension also runs standalone for a targeted audit. Never edits code.

0 on GitHubby Jon (JR) Pricev0.1.1updated 29 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin audit-code in jon-the-dev/claude-code-plugin-marketplace-v0. Commands read from the repo's manifest — 28 days ago.

What it installs

Skills (9)

  • audit-code-architecture

    Read-only architecture audit of a codebase. Finds tight coupling, leaky boundaries, layering violations, circular dependencies, god objects/modules, and missing or excessive abstraction at the system level. Use when the user asks to "audit the architecture", "review module boundaries", "find circula

  • audit-code-correctness

    Read-only correctness audit of a codebase. Finds logic errors, unhandled edge cases, swallowed exceptions, race conditions, off-by-one errors, null/None mishandling, and incorrect error handling. Use when the user asks to "audit correctness", "find logic bugs", "check edge-case handling", "are there

  • audit-code-dependencies

    Read-only dependency audit of a codebase. Finds outdated or known-vulnerable packages, unused dependencies, unpinned/floating versions, license risk, and unjustified new dependencies. Use when the user asks to "audit dependencies", "check for vulnerable packages", "find unused dependencies", "are ve

  • audit-code-master

    Read-only multi-agent codebase audit orchestrator. Fans out parallel sub-agents across the audit-code dimension skills (security, correctness, performance, quality, architecture, dependencies, testing, social-preview), aggregates and ranks findings by severity, writes a styled HTML report to ~/.repo

  • audit-code-performance

    Read-only performance audit of a codebase. Finds N+1 queries, O(n^2) loops, blocking I/O on async paths, unbounded memory growth, missing database indexes, redundant work, and chatty network calls. Use when the user asks to "audit performance", "find perf issues", "why is this slow?", "check for N+1

  • audit-code-quality

    Read-only audit of code quality, readability, and "AI slop". Finds monolithic functions and giant files, duplicate logic paths (the same number computed four slightly different ways), poor variable reuse and naming, dead code, copy-paste, over-abstraction, and code that's hard to understand or shoul

  • audit-code-security

    Read-only security audit of a codebase. Finds hard-coded secrets, authn/authz gaps, injection (SQL/command/template), OWASP Top 10 issues, IaC misconfig, unsafe deserialization, missing input validation, and insecure defaults. Use when the user asks to "audit security", "security review the code", "

  • audit-code-social-preview

    Read-only audit of website social-share previews and launch metadata. Finds missing or weak Open Graph, Twitter/X Card, canonical URL, favicon/app-icon, and social image wiring; verifies deployed image reachability and dimensions when a URL is available. Use when the user asks to check social previe

  • audit-code-testing

    Read-only audit of a codebase's tests. Finds coverage gaps, untested error and edge paths, tests that assert implementation instead of behavior, flaky patterns, over-mocking, and missing regression tests. Use when the user asks to "audit the tests", "review test coverage", "are the tests any good?",

View source on GitHub

Problems found in this repo's manifests

  • .claude-plugin/marketplace.json is not valid JSON

More from jon-the-dev/claude-code-plugin-marketplace-v0

All 7 plugins →

runway

claude

Comprehensive Runway infrastructure deployment management with agents, commands, and hooks

1 skill · 3 commands · 5 agents · 2 MCP servers

0

Senior language and framework specialist agents: fastapi-developer, node-specialist, react-specialist, rust-engineer, typescript-pro, and vue-expert

6 agents

0

DevOps and platform agents: terraform-agent (HCP Terraform workflows via the bundled Terraform MCP server), github-actions-expert (secure CI/CD workflows), owasp-compliance (OWASP ASI Top 10 agent security checks), and api-architect (layered API client code generation)

4 agents · 1 MCP server

0

AI-assisted development workflow suite. Plans and runs sprints (mini-sprint), picks up and ships the next GitHub issue in an isolated worktree with auto-merge on green CI (next-issue), and generates GitHub issue reports with historical burndown tracking (issue-report). Optional: the mini-sprint/next-issue code-review step uses /codex:review from OpenAI's codex plugin (/plugin install codex@openai-codex); the step is skipped if it isn't installed.

3 skills

0

gemini

claude

Cross-model AI assistant via Google Gemini CLI for plan verification, QA review, context offloading, and cross-validation

1 skill

0

Adds a /review command for quick code reviews

1 command

0

Maintain audit-code?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins