Stats
Actions
Available In
Tags
Plugin
cto-toolkit
Learn and retain knowledge across Claude Code sessions with automated quizzes and a defense gate that blocks risky Bash calls until you confirm understanding.
Learn and retain knowledge across Claude Code sessions with automated quizzes and a defense gate that blocks risky Bash calls until you confirm understanding.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Adversarial architecture reviewer agent. Challenges proposed decisions by playing devil's advocate — stress-tests ADRs, finds hidden risks, questions assumptions, and validates alignment with the project's Architectural Identity. Invoke when the user says 'review this ADR', 'challenge this decision', 'devil's advocate', 'stress test this architecture', 'adversarial review', 'poke holes in this', or after completing Phase 2 of the Philosophy-First ADR process.
Autonomous architecture health analyzer. Scans the entire codebase to assess architectural quality — dependency direction, coupling, cohesion, layer separation, and anti-patterns. Produces a structured Architecture Health Report with severity-ranked findings and concrete refactoring recommendations. Invoke when the user says 'review the architecture', 'assess codebase health', 'find architectural issues', 'dependency analysis', or wants a high-level view of code quality across the project.
Autonomous project onboarding agent. Explores an entire codebase and generates a comprehensive Developer Onboarding Guide — project overview, architecture map, key modules, development workflow, coding conventions, and 'where to find things' reference. Invoke when the user says 'onboard me', 'explain this project', 'how does this codebase work', 'new developer guide', 'project walkthrough', 'help me understand this repo', or when a new team member needs to get up to speed on an existing project.
Autonomous release readiness assessor. Evaluates whether a project is ready for production deployment by checking code quality, test coverage, security posture, documentation, observability, rollback plan, and operational readiness. Produces a Go/No-Go Release Report. Invoke when the user says 'are we ready to deploy', 'release checklist', 'go/no-go', 'pre-production check', 'launch readiness', 'deploy assessment', or before any major release or go-live.
Autonomous security audit agent. Performs a comprehensive security scan of the entire codebase — secrets detection, vulnerability patterns, authentication/authorization review, dependency audit, and OWASP Top 10 assessment. Produces a Security Audit Report with severity-classified findings and remediation steps. Invoke when the user says 'security audit', 'scan for vulnerabilities', 'check for secrets', 'OWASP review', 'security assessment', or wants a thorough security analysis of the project.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
The ultimate Claude Code plugin for engineering leadership — 54 skills, 6 autonomous agents, 9 automation scripts, 9 intelligent hooks, and workflow orchestrators covering the full software engineering lifecycle. Now with declarative skill activation, model routing, and continuous learning.
Built for CTOs, VPs of Engineering, Staff Engineers, and Tech Leads who ship production software.
session-learning.sh Stop hook tracks session patterns (languages, tests, security activity) and generates improvement insights every 10 sessionsSessionStart hook scans the project, detects frameworks/file patterns, and suggests relevant skills automatically at the start of each sessionPostToolUse hook detects when security-critical or financial files are edited and suggests deeper analysis with opus-tier modelsPreToolUse hook intercepts production deployment commands and verifies safety (explicit env, no --force, dry-run first)depends-on for optimal execution ordering via topological sortAutonomous subagents that scan your codebase and produce comprehensive reports without manual guidance. Agents now declare model-routing with escalation rules — they start at a cost-efficient tier and upgrade to opus when critical findings are detected.
| Agent | Model | What it does |
|---|---|---|
architecture-reviewer | sonnet → opus | Scans the entire codebase and produces an Architecture Health Report with scores by dimension |
security-auditor | opus | Full security audit — secrets, OWASP Top 10, auth, injection, dependencies |
adversarial-reviewer | opus | Challenges architectural decisions — stress-tests ADRs, finds hidden risks, devil's advocate |
tech-debt-analyzer | sonnet → opus | Inventories all tech debt, prioritizes by ROI, produces a sprint reduction plan |
onboarding-guide | sonnet → opus | Explores the project and generates a complete Developer Onboarding Guide |
release-readiness | sonnet → opus | Evaluates production readiness — Go/No-Go report across 7 dimensions |
| Skill | What it does |
|---|---|
full-review | Orchestrates code review + security + performance + database + architecture + testing into one consolidated report |
health-check | Runs architecture, tech debt, and security analysis to produce a Project Health Dashboard with scores and roadmap |
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 claimnpx claudepluginhub camilooscargbaptista/cto-toolkit --plugin cto-toolkitComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
JeffallanHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
affaan-mDevelop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Randroids-DojoComprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
anthropicsCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
obraTools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
anthropics