38 agents available across all bundles.
| Agent | Model | Description |
|---|---|---|
| ai-consultant | opus | Elite AI strategy consultant for SMBs and mid-market enterprises. Runs full consulting engagements from discovery to delivery using McKinsey, BCG, Deloitte, EY, and Bain methodologies adapted for smaller companies. |
| architect | opus | System design architect. Use for architecture planning, design tradeoffs, execution plans, and coordinating backend/frontend agents. |
| calibrate-best-practices | sonnet | Calibrate sub-agent: extracts best practices from the local codebase or generates industry best practices for the detected stack — writes to .claude/knowledge/shared/best-practices.md |
| calibrate-evaluator | haiku | Calibrate sub-agent: evaluates all toolkit agents, skills, and hooks against project scan results — scores relevance, maps workflows, identifies gaps |
| calibrate-installer | sonnet | Calibrate sub-agent: installs MCP servers, toolkit categories, custom agents/skills, and updates CLAUDE.md based on user-approved recommendations |
| calibrate-knowledge | haiku | Calibrate sub-agent: initializes and seeds the project knowledge base — directory structure, templates, conventions, domain rules, vocabulary |
| calibrate-profiler | haiku | Calibrate sub-agent: synthesizes scanner and evaluator output into .claude/project-profile.md — the file all agents read at runtime |
| calibrate-scanner | haiku | Calibrate sub-agent: deep project scan — platform detection, architecture patterns, coding conventions, testing patterns, domain model, integrations, and environment discovery |
| code-reviewer | inherit | Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. |
| competitive-analyst | sonnet | World-class competitive intelligence analyst synthesizing methodologies from Michael Porter, W. Chan Kim & Renée Mauborgne, Ben Thompson, Hamilton Helmer, Rita McGrath, and April Dunford. |
| completion-verifier | sonnet | Verifies skill outputs are complete against their inputs. Fires as the final step of workflow skills. |
| content-strategist | sonnet | World-class content strategist and copywriter synthesizing methodologies from Ann Handley, Joe Pulizzi, Joanna Wiebe, Andy Crestodina, Robert Rose, and April Dunford. Creates blog posts, landing pages, social copy, and product announcements with codebase context and positioning alignment. |
| design-spec-writer | sonnet | Writes a designer-facing design spec HTML file (.claude/specs/ |
| design-studio:create | opus | Hub agent for world-class product design. Orchestrates design thinking, implementation, and critique into cohesive design-to-code workflow. |
| design-studio:critique | haiku | Expert design review agent. Evaluates designs against world-class standards using the 4 Lenses framework (Rams, Norman, Vignelli, Spool). |
| design-studio-think | sonnet | Design thinker — UX research, user journey mapping, and design briefs for any project |
| explore-light | haiku | Fast, cheap codebase exploration using Haiku. Use for finding files, searching code, reading and summarizing code structure. |
| frontend | sonnet | Adaptive frontend developer — React, Next.js, Vue, Nuxt, Svelte, SvelteKit, Angular, Solid, Astro, Remix, and more. Reads project profile to match the project’s actual framework, patterns, and conventions. |
| gtm-expert | opus | World-class Go-To-Market strategist for modern product launches. Synthesizes methodologies from Nikita Bier, April Dunford, Maja Voje, Wes Bush, Emily Kramer, and Sean Ellis. |
| meeting-prep | haiku | World-class meeting preparation agent grounded in meeting science from Rogelberg, Lencioni, Priya Parker, Pittampalli, Lara Hogan, and Julie Zhuo. Generates pre-meeting briefings from project data and extracts post-meeting action items. |
| ops | haiku | Ops agent — local dev orchestration, startup, testing, and debugging |
| performance | sonnet | Performance optimization agent — scalability, latency, and perceived performance. Applies practices from Google, Netflix, Meta, Shopify, and Cloudflare to audit, profile, and optimize code. |
| product-manager | opus | World-class product manager agent with strategic product sense, growth hacking expertise, and design intuition. Synthesizes methodologies from Shreyas Doshi, Marty Cagan, Lenny Rachitsky, Sean Ellis, Gibson Biddle, Julie Zhuo, and Brian Balfour. |
| backend | sonnet | Adaptive backend developer — Python (FastAPI, Django, Flask), Node.js (Express, NestJS, Hono, Fastify), Go, Rust, Ruby (Rails), Java (Spring), Elixir (Phoenix), and more. Reads project profile to match the project’s actual framework, patterns, and conventions. |
| qa-baseline-updater | sonnet | QA baseline updater — manages test snapshots and golden files for API response validation |
| qa-challenger | sonnet | Adversarial QA agent that red-teams test plans. Reads the diff, knowledge base, and test plan to find gaps the test strategy missed. |
| qa-domain | sonnet | Domain logic quality evaluator. Validates business logic integrity — state machines, enum consistency, constraint rules, and domain-specific correctness. |
| qa-e2e-gen | sonnet | Generates exploratory Playwright tests from git diffs. Maps changed components to routes, synthesizes tests for happy paths, error states, edge cases, and accessibility. |
| qa-e2e | sonnet | E2E test specialist — Playwright browser tests for user workflows, axe-core a11y injection, network/console failure listeners, auth fixture, form-validation flows, and error-page coverage. Uses qa-support.ts helpers from examples/playwright-support/. |
| qa-ios | sonnet | iOS simulator-based visual QA via xcrun simctl + computer-use MCP. Boots iPhone simulator, installs .app bundle, navigates configured screens with screenshot-and-tap sequences, writes per-screen pass/fail findings. |
| qa-test-promoter | haiku | Converts generated test scenarios that caught real bugs into permanent baseline test files. Writes provenance to qa-knowledge. |
| qa-visual | sonnet | Visual regression QA using computer-use MCP (screenshots) and claude-in-chrome (DOM navigation). Captures desktop (1280x800), tablet (768x1024), and mobile (375x812) viewports. |
| qa | sonnet | QA orchestrator — testing across backend, frontend, and E2E layers |
| setup | sonnet | Project setup agent — bootstraps repos from scratch with env, infra, credentials, CI, deploy, and Discord |
| sre | sonnet | SRE agent — deployment, monitoring, incident response for any platform |
| stakeholder-reporter | haiku | Generates plain-English project status reports from git history, GitHub issues, and PRs. Translates engineering activity into business outcomes for non-technical stakeholders. |
| troubleshooter | sonnet | Specialized debugging agent for when other agents get stuck. Performs root cause analysis using error context, knowledge base, git history, and CLAUDE.md. |
| user-researcher | sonnet | World-class user researcher synthesizing methodologies from Teresa Torres, Rob Fitzpatrick, Erika Hall, Steve Portigal, Indi Young, and Clayton Christensen. Expert in continuous discovery, interview design, feedback synthesis, persona generation, JTBD analysis, and opportunity mapping. |
Auto-generated on 2026-07-16