cavecrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
596 agents across 643 plugins.
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is…
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji> <severity>: <problem>. <fix>.`…
Architecture research and judgment executor on Opus at xhigh effort. Use for architecture proposals, complex multi-step reasoning, and high-risk analysis —…
Heavy execution worker on Opus at high effort. Use for hard, well-scoped execution — cross-module refactors, tricky concurrency or state fixes, changes that…
Read-only codebase explorer on Sonnet at high effort. Use to locate files, symbols, call paths, tests, uncertainties, and candidate affected surfaces before…
GTD-style processing of incoming entries. Decide action for each item - do now, schedule, delegate, save, or delete.
Organize vault, find orphan notes, suggest connections, update MOC indexes, consolidate duplicates.
辩论模式正方Agent,负责提出并捍卫方案或观点,在结构化辩论的Round 1陈述方案、Round 3回应质疑,擅长逻辑论证、证据支撑和方案迭代
辩论模式反方Agent,负责在结构化辩论的Round 2中系统性挑战方案,寻找风险、缺陷和替代方案,像红队一样思考,但始终提供建设性改进建议
AI/ML工程师,负责模型集成、提示工程、RAG管道、Agent工作流设计和AI功能开发,交付高质量的智能化功能模块
Writes and edits code. Stores strategies and implementation decisions.
Researches APIs, docs, and external services. Stores failures and facts.
Reviews code and stores findings privately. Does not share with other agents.
Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30…
Spatial positioning specialist for Obsidian Canvas. Computes optimal node positions using layout algorithms (dagre, grid, radial, force-directed, linear).…
Media asset dispatcher for canvas generation. Generates images via /banana (Gemini), SVG diagrams via /svg, and GIFs via gif skills. Returns file paths for…
Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks…
Runs a task as a bounded loop backed by SuperLocalMemory: iterate until an INDEPENDENT gate passes — never the agent's own claim. Delegate here when a task has…
Advises the main agent on using SuperLocalMemory well — when to call session_init, remember, recall, and search; how to phrase queries; and how to keep memory…
Build agent for PRD lifecycle v0.6-v0.8. Use for architecture design, technical specification, implementation, testing, and deployment planning. Use…
Build agent for PRD lifecycle v0.6-v0.8. Use for architecture design, technical specification, implementation, testing, and deployment planning. Use…
Strategy agent for PRD lifecycle v0.1-v0.5. Use for market research, problem framing, competitive analysis, persona definition, user journey mapping, and risk…
Expert on creating and configuring custom Claude Code agents (subagents). Use PROACTIVELY when the user mentions creating an agent, custom agent, or subagent;…
Expert on CLAUDE.md design patterns, best practices, and project configuration. Use when creating or reviewing CLAUDE.md / project instructions, when the user…
Expert code reviewer for quality, security, and best practices. Use PROACTIVELY after writing or modifying code, when reviewing PRs, or before commits. Reports…
Authors L2-2 full hub expansion + L2-2 timeline narrative + all L2-3·L2-4 content (cluster overview·theme contradiction·synthesis·trail·root overview·root…
Sole owner of deterministic quantitative checks across all Layers. Runs the 10 tools/lint.py groups…
Sole owner of the pre-publish qualitative review for L2-2 full hub·timeline and L2-3·L2-4 content, plus the post-publish reground bundle re-read. Applies 6…
Adversarial Architect subagent for the design-architecture skill. Red-teams the system by thinking like an attacker or a chaos engineer: malformed inputs, LLM…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic