By hrconsultnj
Detects test frameworks, analyzes existing conventions to generate matching tests, runs tests for changed files or full suite with failure reports, and validates multi-system integrations while maintaining consistent file encoding.
Calibrate test bench — detect test framework, read existing test conventions, generate .claude/testbench.json config. Query Context7 for test framework reference docs. Run once per project.
Generate tests for a file or function. Convention-aware -- reads existing test files first to match project style. One file at a time.
Run tests -- all, changed files only, or for a specific file. Parse output, show failures with source context.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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.
Claude writes code fast. These plugins make sure it writes it right.
5 plugins · 33 skills · 17 automated hooks · 13 MCP tools · 8 indexed languages · One command setup
Full docs & getting started: composure-pro.com
AI coding agents are fast — but speed without guardrails creates expensive cleanup work. If you've used Claude Code on a real project, you've seen this:
as any, @ts-ignore, non-null assertions to silence errors instead of fixing typeseval(), SQL injection vectors slip through unnoticedYou can write better prompts. You can add more rules to CLAUDE.md. But the agent can still ignore all of it — instructions are suggestions, not enforcement.
Hooks are different. They run as shell scripts on every Read/Edit/Write — outside the LLM, at zero token cost. The agent literally cannot bypass them. That's how these plugins work.
All plugins, all skills, all hooks — free for personal use, education, and nonprofits.
| What | Count | Details |
|---|---|---|
| Plugins | 5 | Composure, Design Forge, Sentinel, Testbench, Shipyard |
| Skills | 33 | Architecture, blueprinting, security scanning, test generation, CI/CD, audits, integrations |
| Hooks | 17 | Code quality, secret detection, type safety, decomposition, graph updates |
| MCP tools | 13 | Graph queries, semantic search, reference search, dependency chains, audits, reports |
| Reference docs | 23 | Security patterns, testing patterns, deployment guides |
| Templates | 12 | Test files, GH Actions workflows, Dockerfiles |
| Hook enforcement | 7 languages | TypeScript, Python, Go, Rust, C++, Swift, Kotlin |
| Graph indexing | 8 languages | TypeScript, JavaScript, SQL, JSON, YAML, Markdown, ENV, Prisma |
| Graph node types | 13 | Functions, Classes, Types, Tables, Columns, RLS Policies, Indexes, Packages, Scripts, and more |
| Plugin | What it solves |
|---|---|
| Composure | Code quality enforcement — decomposition hooks, architecture skills, code review knowledge graph, severity-tracked task queue. The foundation that all other plugins build on. |
| Sentinel | Security scanning — SAST, secret detection on every write, dependency CVE audit, HTTP header analysis. Local-first, no cloud auth. |
| Testbench | Convention-aware test generation — reads your existing tests to match project style. Nudges when you edit untested files. |
| Shipyard | CI/CD generation and validation — GitHub Actions, GitLab CI, Bitbucket Pipelines. Dockerfile validation, dependency health, production readiness. |
| Composure Pro | 22 production architecture patterns + schema guard hook. Postgres RLS, tenant isolation, entity registry, auth model, type generation — battle-tested across 322+ migrations. Works with any Postgres host. |
| Design Forge | Premium web design patterns — 33 production components, canvas presets, animation recipes, 3D integration, accessibility-first. |
macOS / Linux:
curl -fsSL https://composure-pro.com/install.sh | sh
Windows (PowerShell):
irm https://composure-pro.com/install.ps1 | iex
Windows (Command Prompt):
curl -fsSL https://composure-pro.com/install.cmd -o %TEMP%\composure-install.cmd && %TEMP%\composure-install.cmd
Works on any OS with Claude Code installed:
# Add the marketplace
claude plugin marketplace add hrconsultnj/claude-plugins
# Install Composure
claude plugin install composure@my-claude-plugins
After installing, restart Claude Code and authenticate:
/composure:auth login
npx claudepluginhub hrconsultnj/claude-plugins --plugin testbenchCI/CD generation, deployment preflight, and Dockerfile validation with zero-downtime patterns.
Security scanning, dependency CVE audits, and exposure-aware risk prioritization.
Premium design patterns, UX research skills, and user journey mapping for modern web applications.
Code quality enforcement, architecture skills, structural code graph, and impact-aware reviews.
Code quality enforcement, architecture skills, structural code graph, and impact-aware reviews.
Automated Test-Driven Development enforcement
Commands for code review, testing, and analysis
Generate comprehensive tests for a specific file
TestForge - Master of quality assurance through intelligent test generation. Analyzes code behavior to auto-generate comprehensive tests that catch real bugs, not just boost coverage numbers. Supports Jest, Pytest, Vitest, and more.
Agents specialized in quality assurance, testing strategies, and test architecture. Focuses on ensuring code quality and reliability.