Subagents, all 2,021 of them.
Specialist agents your main agent can delegate to. Browse subagent definitions from the public directories. Add one to your gateway and every agent you use gets it through one link.
2,021 results · page 33 of 68 · 158 low signal or duplicate entries are not listed
- Add
Talent acquisition lead for sourcing, screening, interview-loop design, and pipeline reporting
★ 605
- Add
Cs Tech LeadAI & models
Tech Lead agent for daily architecture reviews, code quality oversight, and tech debt management
★ 605
- Add
Doc GeneratorDocs & knowledge
Generates and updates project documentation automatically. Use proactively after significant code changes, new features, or API modifications. Creates README sections, API docs, architecture docs, and inline documentation.
★ 605
- Add
Git WorkflowAI & models
Manages git operations including branching, committing, PR creation, and release workflows. Use when preparing commits, creating PRs, managing branches, or handling merge conflicts. Enforces conventional commits and branch protection rules.
★ 605
- Add
Skill CreatorAI & models
Authors new skills for this library and grades existing ones against the repo's eval template. Operates in four modes: Create, Grade, Compare, Analyze.
★ 605
- Add
CouncilAI & models
Multi-perspective architectural review with 10 specialized perspectives via real multi-agent deliberation.
★ 332
- Add
Council ArchitectDev tools
Systems thinking, backwards compatibility, and long-term stability review (Linus Torvalds inspiration)
★ 332
- Add
Council BenchmarkerDev tools
Performance-obsessed, benchmark-driven analysis demanding measured evidence (Matteo Collina inspiration)
★ 332
- Add
Council DeployerCloud & infra
Zero-config deployment, CI/CD optimization, and preview environment review (Guillermo Rauch inspiration)
★ 332
- Add
Council ErgonomistDev tools
Developer experience, API usability, and error clarity review (Sindre Sorhus inspiration)
★ 332
- Add
Council MeasurerMonitoring & ops
Observability, profiling, and metrics philosophy demanding measurement over guessing (Bryan Cantrill inspiration)
★ 332
- Add
Council OperatorDev tools
Operations reality, infrastructure readiness, and on-call sanity review (Kelsey Hightower inspiration)
★ 332
- Add
Council QuestionerDev tools
Challenge assumptions, seek foundational simplicity, question necessity (Ryan Dahl inspiration)
★ 332
- Add
Council SentinelSecurity
Security oversight, blast radius assessment, and secrets management review (Troy Hunt inspiration)
★ 332
- Add
Council SimplifierDev tools
Complexity reduction and minimalist philosophy demanding deletion over addition (TJ Holowaychuk inspiration)
★ 332
- Add
Council TracerMonitoring & ops
Production debugging, high-cardinality observability, and instrumentation review (Charity Majors inspiration)
★ 332
- Add
EngineerProductivity
Task execution agent. Reads wish from disk, implements deliverables, validates, and reports what was built.
★ 332
- Add
FixAI & models
Bug fix agent. Finds root cause, applies minimal fix, proves it works, reports what changed.
★ 332
- Add
PmDev tools
Project manager. Owns backlog, coordinates teams, full lifecycle (draft to ship), delegates via genie CLI. Load /pm for the playbook.
★ 332
- Add
RefactorDev tools
Refactor specialist. Assesses architecture, plans staged changes, verifies nothing breaks.
★ 332
- Add
Ai Hygiene AuditorAI & models
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
★ 330
- Add
Architecture review for system design, ADR compliance, and coupling analysis. Use for major refactors.
★ 330
- Add
Blast Radius ReviewerFiles & storage
Review code changes using blast radius analysis from the code knowledge graph. Reads high-risk affected files and provides graph-aware review findings.
★ 330
- Add
Bloat AuditorAI & models
Execute progressive bloat detection scans (Tier 1-3), generate prioritized reports, and recommend cleanup actions.
★ 330
- Add
Code RefinerAI & models
Orchestrate code quality refinement: analyze living code for duplication, algorithmic inefficiency, clean code violations, and architectural misfit. Generate concrete refactoring plans with before/after examples. Use PROACTIVELY for: code quality improvement, refactoring sprints, anti-slop remediati
★ 330
- Add
Code Review ModeAI & models
Main thread configuration for evidence-based code review sessions. Focuses on systematic review with evidence gathering and structured findings. Use via: claude --agent code-review-mode Or set in .claude/settings.json: { "agent": "code-review-mode" }
★ 330
- Add
Code SearcherSearch
Search GitHub for existing implementations of a research topic. Returns structured findings with repo metadata, pattern analysis, and relevance ranking. Lightweight agent scoped to code search only.
★ 330
- Add
Commit AgentCommunication
Conventional commit message generation agent specializing in change classification, semantic versioning awareness, and consistent commit formatting. Use when drafting commit messages for staged changes, classifying change types, formatting breaking change footers, linking issues in commits. Do not u
★ 330
- Add
Context OptimizerAI & models
Autonomous agent for context window optimization and MECW compliance. Use when full context audits needed, skills exceed token budgets, pre-release compliance verification, periodic health checks. Do not use when single skill optimization - use optimizing-large-skills skill. quick token counts - use
★ 330
- Add
Continuation AgentFiles & storage
Lightweight agent designed to continue work from a session state checkpoint. Spawned when the parent agent exceeds context thresholds. This agent: 1. Reads the session state file 2. Re-establishes necessary context 3. Continues the task without interruption 4. Can spawn another continuation agent if
★ 330
