architect
01Agent Claude Code
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Public Pi Coding Agent setup with curated agents, skills, MCP config, safety defaults, and workflow extensions.
Agent Claude Code
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Agent Claude Code
Independent post-finalization code reviewer. Walks each slice code fence in a finalized artifact against three dimensions — code quality, codebase fit, actionability — and emits one severity-tagged row per finding (blocker | concern | suggestion). Use whenever a finalized plan or design needs adversarial vetting of…
Agent Claude Code
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
Agent Claude Code
The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.
Agent Claude Code
Finds relevant documents in .rpiv/artifacts/. The research equivalent of codebase-locator. Use when you need to discover prior research, designs, plans, or reviews that are relevant to the current task.
Agent Claude Code
Automatic routing mode - choose the best agent/mode for the request, then proceed with the right workflow.
Agent Claude Code needs its repo
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
Agent Claude Code
Default implementation agent - make code changes with tests and verification.
Agent Claude Code
Adversarial finding verifier. Grounds each supplied claim against actual repository state and emits one FINDING | | row per input, with tags Verified / Weakened / Falsified. Tier: git-analyzer (+ bash for git show). Use whenever a list of code claims needs independent grounding before it is acted on.
Agent Claude Code
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Agent Claude Code
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).
Agent Claude Code
Locates files, directories, and components relevant to a feature or task. Call codebase-locator with a human-language prompt describing what you're looking for. A "super grep/find/ls" tool. Reach for it when you would otherwise reach for grep, find, or ls more than once.
Agent Claude Code
You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.
Agent Claude Code
PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.
Agent Claude Code
Frontend UI/UX specialist who creates intentional, polished user experiences. Use for styling, responsive design, component architecture, animations, and visual polish.
Agent Claude Code
Row-only patch auditor. Walks a patch against a caller-supplied surface-list and emits one pipe-delimited row per finding (file:line | verbatim | surface-id | note). Use whenever a diff needs evidence-only enumeration of matching patterns, with no narrative or severity.
Agent Claude Code
Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/, updates READMEs and guides.
Agent Claude Code
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
Agent Claude Code
Read-only project exploration subagent. Use this first when you need to locate files, symbols, patterns, ownership boundaries, references, wiring, tests, or implementation entry points before planning or editing. Returns exact path:line evidence, ruled-out areas, and open questions. Never edits or implements.
Agent Claude Code
Fast implementation specialist. Receives complete context and task spec, executes code changes efficiently. Use for well-defined tasks with clear specs - no research, no planning, just execution.
Agent Claude Code
Finds what connects to a given component or area: inbound references, outbound dependencies, config registrations, event subscriptions. The reverse-reference counterpart to codebase-locator. Use when you need to understand what calls, depends on, or wires into a component.
Agent Claude Code
Analyze media files (PDFs, images, diagrams, screenshots) that require interpretation beyond raw text. Extracts information, describes visual content. Uses vision-capable models.
Agent Claude Code
Intelligent task orchestrator that analyzes requests and delegates to specialized agents. Use as the default agent for complex tasks requiring planning, implementation, and review.
Agent Claude Code
Pairwise peer-invariant comparator. Given (newfile, peerfile) pairs, tags each peer invariant Mirrored / Missing / Diverged / Intentionally-absent against the new file. Use when an entity parallels an existing sibling (aggregate, service, handler, reducer, repository) and the new file must be checked against the…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: