Orchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dependencies and QA gates that survive every session - not buried in chat history.
Agent Claude Code
External research and synthesis. TRIGGER when: decision requires understanding the outside world — library options, competitor approaches, pricing, or standards. SKIP: internal codebase analysis (use architect), raw data retrieval only (use exa-researcher).
Agent Claude Code
Pre-task analysis and architecture design. TRIGGER for all tasks, without exception — mandatory gate before any sub-agent is spawned. Main Agent provides raw task description and codebase context; architect determines task boundaries and returns decomposition. SKIP: implementation, external technology research …
Agent Claude Code
Implements bounded delivery slices with clear acceptance criteria. TRIGGER when: (1) task has explicit files-to-modify and definition of done, (2) slice is single-role with no architectural uncertainty, (3) the mandatory architect decomposition gate has already been cleared for this task. SKIP: strategic decisions…
Agent Claude Code
Searches across Exa verticals — people, company, code, news. TRIGGER when: (1) task requires external information, competitive intelligence, or recent news, (2) finding code examples or library options. SKIP: internal codebase analysis (use architect), synthesis and recommendations (use analyst).
Agent Claude Code
Production-grade UI implementation with high design quality. TRIGGER when: (1) building web components, pages, or dashboards, (2) styling or beautifying any web UI, (3) design brief is provided or inferable. SKIP: backend logic, data layer, tasks needing no UI output. Dashboards/web-UI overlap: frontend-design…
Agent Claude Code
Creates and updates process docs, templates, decision artifacts, and agent specs. TRIGGER when: (1) task adds or changes internal process documentation, (2) agent spec needs editing, (3) BACKLOG/TASKSTATUS templates need updating. SKIP: user-facing docs (use technical-writer), code changes.
Agent Claude Code
Validates completed slices against acceptance criteria. TRIGGER when: (1) developer marks a slice devdone or readyforqa, (2) runtime or manual verification is required. SKIP: artifact-only or unit-only tasks (validator run / test suite serves as QA), tasks still inprogress.
Agent Claude Code
Performs security audits on code slices. TRIGGER when: requiressecurityreview is true, or task adds/modifies external inputs, auth flows, or third-party integrations. SKIP: internal refactors with no new attack surface — reports only, does not fix code.
Agent Claude Code
Creates and updates user-facing project documentation. TRIGGER when: (1) task produces README, Getting Started guide, API reference, CHANGELOG, or tutorial, (2) external users need to understand the project. SKIP: internal process docs, BACKLOG/TASKSTATUS templates, code changes.
Agent Claude Code
Autonomous UI designer working in Figma. TRIGGER when: (1) reading/inspecting Figma files, (2) generating design tokens or Code Connect mappings, (3) exporting assets or producing design specs. SKIP: source code changes (Code Connect .figma.ts files only), tasks without FIGMAACCESSTOKEN.
Agent Claude Code
Reviews interfaces and document structures for scan order, hierarchy, and clarity. TRIGGER when: (1) requiresux is true, (2) panel hierarchy or operator surface needs review. SKIP: implementation, strategic decisions — observes and recommends only, does not edit files. Dashboards/web-UI overlap: ux reviews only (no…
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: