The Composure Suite
One install. Six systems. Zero configuration.
6 plugins. 49 skills. Each specialized — together, they share one code graph, one task queue, and one commit gate.
How the plugins connect
One shared data model — graph, tasks, and commit gate — binds all five plugins into a single system.
Composure
FREEArchitecture & code quality
19 skillsView plugin
Skills
/composure:about— One-page overview — what Composure does, common workflows, full skill catalog. Run when a user asks 'what does Composure do' or wants an orientation./composure:app-architecture— Master router to framework-specific architecture guides. Detects stack, routes to frontend/fullstack/mobile/backend docs./composure:audit— Full audit across 5 categories: Architecture, Security, Code Quality, Dependencies, Test Coverage. Letter grades A-F./composure:backlog— Processes accumulated code quality tasks. Modes: batch (sequential), delegate (parallel sub-agents), verify, archive, clean, sync.PRO/composure:blueprint— Graph-powered planning with progressive refinement. Classifies work, scans code graph for related files, confirms scope with user, analyzes impact, writes implementation spec.PROTrial · 3/day/composure:build-graph— Creates or updates the code knowledge graph. Parses source files with tree-sitter, maps imports, identifies functions/types/components, builds dependency graph./composure:changelog— Auto-generates changelog from git history enriched with code graph entity mapping. Groups by conventional commit type./composure:code-organizer— Restructures disorganized projects into conventional layouts. Detects file types, maps to appropriate directories, executes moves with import updates.PRO/composure:commit— Commits with automatic task queue hygiene. Cleans resolved tasks, archives completed audits, blocks if staged files have open Critical/High items./composure:cortex— Direct interface to the Cortex memory system. Search, create, traverse, and manage memory nodes and edges.PRO/composure:doc-compose— Admin-only content composition engine. Resolves {{import}} directives and conditional rendering for multi-surface documentation.ENTERPRISE/composure:health— Plugin diagnostics — version, auth, hooks, graph, tasks./composure:integration-builder— Stack-agnostic third-party integration scaffolding. Detects your project language, pulls latest SDK docs via Context7, and scaffolds client, auth, webhooks with proper error handling.PRO/composure:mcp-builder— Build custom MCP servers to connect any service to Claude Code. Discovers the target API, designs tool definitions, and scaffolds a complete TypeScript MCP server project.PRO/composure:mcp-install— Discover and configure existing MCP servers for your project. Stack-aware recommendations from a curated registry with full setup — install, configure, and verify./composure:critique-local— Token-efficient review of only changed code and its blast radius. Uses graph to auto-detect impact.PROTrial · 5/day/composure:critique— Comprehensive PR review using the code graph. Identifies changes, resolves linked issues, builds structural context, generates walkthrough, runs quality audit.PROTrial · 5/day/composure:pursue— Drive a goal to completion through a gated, resumable, multi-stage campaign — audit → organize → blueprint → build → verify — looping back until an acceptance gate is met. Orchestrates existing skills rather than reimplementing them; pairs with native /goal.PROTrial · 3/day/composure:session-summary— Generate a full session rollup — commits, tasks completed, key decisions, and open items. Appends to today's session file.Sentinel
FREESecurity scanning
5 skillsView plugin
Skills
/sentinel:assess— Assesses your project's security surface — detects stack, package managers, security tooling, and integrations. Generates config for ongoing scanning./sentinel:scan— Combines Semgrep static analysis and dependency audit. Writes findings to tasks-plans/tasks.md with severity mapping.PRO/sentinel:audit-deps— Focused vulnerability audit. Reports CVEs with installed/fixed versions and exact upgrade commands./sentinel:headers— Analyzes security headers for a given URL. Context-aware grading based on exploitable risk, not checkbox compliance./sentinel:package-risk— Analyzes an installed package's source code for suspicious behavior patterns — eval calls, network requests, environment access, and obfuscation.PROShipyard
FREECI/CD & deployment
6 skillsView plugin
Skills
/shipyard:configure— Detects CI/CD platforms, deployment targets, container configs. Generates .claude/shipyard.json.PRO/shipyard:ci-generate— Generates production-ready CI/CD workflows from detected stack. Shows diff before overwriting existing workflows.PRO/shipyard:ci-validate— Validates workflows using actionlint + built-in heuristic checks./shipyard:dockerfile— Generates or validates Dockerfiles with security best practices. Framework-specific multi-stage builds.PRO/shipyard:deps-check— Broader than Sentinel — includes outdated packages. Determines highest-safe-version accounting for cascading vulnerabilities./shipyard:preflight— Production readiness checklist. Checks environment variables, health endpoints, error monitoring, CORS, rate limiting, and security headers.Testbench
FREEConvention-aware testing
3 skillsView plugin
Skills
/testbench:calibrate— Detects test framework (Vitest, Jest, Playwright, Cypress, pytest, Go test, Cargo test, RSpec, PHPUnit). Reads conventions. Generates config./testbench:generate— Generates tests for a single file. Reads config AND existing test files, never generates without context.PRO/testbench:run— Runs tests with scope control: all, changed files only, or single-file. Parses output, extracts failures with source context.Design Forge
FREEPremium design patterns
12 skillsView plugin
Skills
/design-forge:intake— Four quick questions — what you're building, your design system, brand assets, and motion level — turn a vague "make it look good" into a precise brief every downstream Design Forge skill reads, so you never re-explain your intent. Native AskUserQuestion at each step; re-run to change a single answer.PRO/design-forge:ingest— Lift a real design system into Design Forge in seconds — point it at your current project, a GitHub repo, a named shadcn theme, or a live URL and it extracts the colors, typography, and spacing tokens every generator then matches. No manual token entry; network calls are consent-gated with graceful fallback.PRO/design-forge:product-planner— Map user types, goals, flows, screens before coding.PRO/design-forge:ui-designer— Browse and apply premium web design patterns — taxonomy routing, section templates, asset generation, component catalog. Plus premium web animations, 3D, creative coding, generative art, and interactive experiences.PRO/design-forge:ux-researcher— AI-powered design research agent using WebSearch and WebFetch to discover patterns, evaluate competitors, analyze technologies.PRO/design-forge:analyze-market— Snapshot any market in one pass — competitor features, live pricing, positioning, and the open gaps — turned into a feature matrix, a pricing table, and a positioning quadrant you can act on. Grounds branding and compose so your design decisions answer a real competitive picture, not a guess.PRO/design-forge:branding— Turn "I need a logo" into a real, versatile brand identity: a validated name (trademark, domain, and category-collision checked), a full logo system — wordmark, icon, lockup, and an optional mascot — in light/dark/transparent variants, plus palette, type, and a brand board. It grounds itself first by running the market + design research, asks whether you even need a domain, then generates the marks as HTML rendered to image so they stay crisp and on-brand. Free for everyone./design-forge:compose— Drive a whole brand/marketing surface — a website, a funnel, a landing page, or a pitch deck — to completion as one gated, resumable, autonomous campaign. It orchestrates the Design Forge skills end-to-end (intake -> research -> copy -> build -> verify) on a single verified Positioning Foundation, hard-gates the build until the positioning is actually locked, and doesn't stop until the result renders and lands. Pursue, for design.ENTERPRISE/design-forge:copywriter— Generate conversion-grade website and marketing copy from your customers' own language. It mines voice-of-customer, picks the message strategy that actually moves your specific buyer, builds a pillar-and-proof message house, and writes section-by-section copy keyed to your design — including a "sell yourself" mode for founders and experts who position other people's products brilliantly but undervalue their own.ENTERPRISE/design-forge:go-to-market— Get the built site found. The off-site distribution layer: it adapts to how your business actually gets discovered, audits your current footprint, and produces a 30/60/90 plan plus ready-to-use assets — Google Business Profile, local SEO, AI-citability, the zero-reviews cold-start, and channel recommendations by industry. Compose builds the business card; this hands it out.ENTERPRISE/design-forge:seo— Make the site findable by Google and by AI answer engines. It generates the on-site artifacts straight from your brand foundation — metadata, sitemap, robots with the correct retrieval-bot allowlist, JSON-LD for the schema that still earns rich results, OG images, and answer-first structure — then audits and validates them. AEO/GEO is built in, and it's current to 2026 (Next.js-aware).ENTERPRISE/design-forge:social-media— Turn one positioning pillar into 20-50 platform-native posts. It atomizes a verified message pillar, packages each one natively per channel (never copy-paste), meets each audience on the channels they already use, anchors every post to verified proof, and runs a 2026 authenticity pass — then hands you drafts and a content calendar. It never auto-publishes; you edit and post.ENTERPRISECortex
PROAI memory & reasoning persistence
4 skillsView plugin
Skills
/composure:cortex— Direct interface to the Cortex memory system. Search, create, traverse, and manage memory nodes and edges.sequential_think— Persistent chain-of-thought reasoning that survives across sessions. Pick up complex analysis exactly where you left off — even weeks later.search_memory— A knowledge network that grows with every session. Nodes and edges form a project-aware memory graph linking decisions, patterns, and learnings.capture_thought— Automatic behaviors that require no commands. Cortex captures reasoning when you use sequential thinking, nudges task creation on complex prompts, and loads relevant memories at session start.