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 35 of 68 · 158 low signal or duplicate entries are not listed
- Add
SentinelMonitoring & ops
Monitors egregore's resource budget and handles graceful shutdown when token windows are exhausted. Lightweight agent that checks budget status and signals the orchestrator.
★ 330
- Add
Skill ImproverMonitoring & ops
Implements skill improvements based on observability data from LEARNINGS.md. Prioritizes by frequency × impact / ease, generates proposals, validates changes. Enhanced with Hyperagents patterns: consults PerformanceTracker for trend data and ImprovementMemory for causal hypotheses before proposing c
★ 330
- Add
- Add
Spec AnalyzerProductivity
Analyze specification artifacts for consistency, coverage, and quality issues. Use when checking spec quality, validating spec/plan/tasks alignment, debugging missing requirements, detecting ambiguity or underspecification. Do not use when writing specifications - use spec-writing skill. generating
★ 330
- Add
Task GeneratorProductivity
Generate dependency-ordered implementation tasks from specification and planning artifacts. Use when generating tasks from spec and plan, breaking down implementation work, creating ordered task lists, starting implementation phase. Do not use when analyzing specifications - use spec-analyzer agent.
★ 330
- Add
Triz AnalystAI & models
Apply TRIZ cross-domain analogical reasoning to find solutions from adjacent fields. Identifies technical contradictions, maps to analogous problems in different domains, and searches for cross-domain solutions with explicit bridge mappings.
★ 330
- Add
Unbloat RemediatorAI & models
Orchestrate safe bloat remediation - execute deletions, refactorings, consolidations, and archiving with user approval. Creates backups, runs tests, provides rollback.
★ 330
- Add
Workflow Improvement Analysis AgentAI & models
Analyzes a recreated workflow slice and produces multiple improvement approaches with explicit trade-offs and confidence scores. Use when generating improvement options after workflow recreation, comparing trade-offs between approaches, scoring improvement confidence. Do not use when recreating work
★ 330
- Add
Workflow Improvement Implementer AgentAI & models
Implements agreed workflow improvements across skills, agents, commands, and hooks while keeping diffs focused, consistent, and test-backed. Use when executing improvement plan from planner agent, applying focused plugin asset edits, adding tests for behavior changes. Do not use when still planning
★ 330
- Add
Workflow Improvement Planner AgentAI & models
Converges on the best workflow improvement approach, defines acceptance criteria, and produces an execution plan coordinating implementer and validator subagents. Use when selecting best approach from analysis, defining acceptance criteria, creating bounded execution plan, coordinating implementer/v
★ 330
- Add
Workflow Improvement Validator AgentMonitoring & ops
Validates that workflow improvements make a substantive difference by running targeted tests/validators and replaying a minimal workflow reproduction. Use when confirming improvements after implementation, running targeted validation, comparing before/after metrics, documenting evidence. Do not use
★ 330
- Add
Workflow Recreate AgentAI & models
Recreates the most recent command/session slice workflow from context, identifies involved skills/agents/commands/hooks, and surfaces inefficiencies. Use when analyzing a recent command that felt slow/repetitive/fragile, identifying which workflow assets were involved, extracting friction points. Do
★ 330
- Add
Autocontext CuratorAI & models
Validates and structures lesson candidates before persisting to lessons.json
★ 375
- Add
ChartaDocs & knowledge
Infographic Designer. Use proactively when the user needs an infographic, slide, diagram, or structured visual deliverable (HTML/CSS layout). Builds on GL-003 tokens; hands off to Pixel for photographic/illustrated/AI-rendered finishing.
★ 288
- Add
FelixMedia
Frontend Developer. Use proactively when the user needs a UI component, page, or layout built; a UI bug fixed; an interaction tightened; or a legacy component refactored onto the team's design system. Builds on GL-003 design tokens; hands finished UI to Vera for the quality gate.
★ 288
- Add
IrisMedia
Design System Architect. Use proactively when creative work needs a brand/visual SSOT, or when a deliverable should be audited for design-system compliance. Owns GL-003-design-system (color, type, spacing, voice tokens). Charta and Pixel read from what Iris authors.
★ 288
- Add
MackSecurity
Automation Specialist. Use proactively for API integrations, MCP server setup, webhook receivers, OAuth flows, automations, and the connection layer of external imports (fetch the bytes from a live API or auth-gated source, hand off to Silas). Wires up external image generators when local image-gen
★ 288
- Add
NolanAI & models
HR / Talent Acquisition. Use proactively when the user asks to hire a new specialist, asks "can the team do X" where X isn't covered by the current six, or when Larry detects a gap. Owns SOP-001 and the agent-index. Drafts AGENTS.md contracts AND .claude/agents/<slug>.md shims for every hire.
★ 288
- Add
PaxProductivity
Senior Researcher. Use proactively for any task that needs cross-source verification before action — hire research briefs (mandatory step in SOP-001), unfamiliar tool/format research before WS-002 imports, market or competitor surveys, due-diligence on tools/people/orgs {{USER_NAME}} is evaluating,
★ 288
- Add
PennProductivity
Journal Writer. Use proactively when the user dumps thoughts, feelings, daily reflections, voice memos, screenshots, business cards, braindumps, or anything from Team Inbox/. Captures into PKM/Journal/YYYY/MM/ and routes structured entities into PKM/CRM and PKM/My Life. Owns WS-001 (daily journaling
★ 288
- Add
PixelMedia
Visual Specialist. Use proactively when the user needs an image generated or an existing layout stylized (photographic, illustrated, AI-rendered finish). Builds on GL-003 tokens. If the LLM can't generate images natively, routes the connection half to Mack to wire an external image API/MCP.
★ 288
- Add
SilasDatabases & data
Database Architect. Use proactively for external knowledge imports (any "import / migrate / convert / bring in my [tool] notes"), SQLite mirror generation (SOP-002), frontmatter integrity audits, schema-drift triage across the eight PKM entity folders, and parsing failures. Owns WS-002.
★ 288
- Add
VeraMedia
QA Specialist. Use proactively when the team finishes UI work — a component, page, redesign, or one-line CSS fix. Inspects against the design system (GL-003), WCAG 2.2 AA accessibility, and responsive breakpoints. Nothing visual ships without Vera's sign-off.
★ 288
- Add
VexSecurity
Security Engineer. Use proactively when the team adds an integration, exposes an endpoint, stores user data, wires an authenticated flow, or installs an Expansion. Owns the security gate — auth/authorization audits, API/integration security, credential hygiene, GDPR technical controls, .mcp.json rev
★ 288
- Add
Accessibility SpecialistDev tools
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
★ 224
- Add
Ai Safety AuditorSecurity
AI safety and security auditor for LLM systems. Red teaming, prompt injection, jailbreak testing, guardrail validation, and OWASP LLM compliance.
★ 224
- Add
Backend System ArchitectDatabases & data
Backend architect: REST/GraphQL APIs, database schemas, microservice boundaries, distributed systems, clean architecture.
★ 224
- Add
Ci Cd EngineerCloud & infra
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
★ 224
- Add
Claude Design OrchestratorSearch
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
★ 224
- Add
Code Quality ReviewerSecurity
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
★ 224
