agent-coordination
Multi-agent orchestration with model routing, category delegation, and sprint management. Use for coordinating Pantheon agents.
agent-evaluation
Evaluate AI agent outputs — hallucination detection, quality scoring, behavioral testing, and CI/CD pipelines.
agent-observability
Observability with OpenTelemetry, metrics, and logging. Use for monitoring agents and LLM calls.
api-design-patterns
Design RESTful APIs with pagination, filtering, and OpenAPI docs. Use for FastAPI endpoint design.
artifact-management
Structured artifact trail for feature implementations — plans, implementations, reviews, and decisions.
auto-continue
Auto-continue through todos with idle detection and safety gates. Use for multi-step orchestration.
cache-strategy
Cache patterns for Redis, CDN, TTL, and invalidation. Use for architecture decisions on caching strategies.
code-review-checklist
Systematic code review with quality gates, security audit, and parallel checks. Use for structured feedback on pull requests.
codemap
Generate codebase maps with directory trees and relationships. Use for onboarding and architecture documentation.
context-compression
Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references
conversational-ai-design
Design conversational AI with Rasa NLU, dialogue management, and LangChain memory patterns.
database-migration
Database migrations with Alembic, rollbacks, and zero-downtime deployment. Use for schema changes.
database-optimization
Optimize SQL queries, indexes, and identify N+1 problems. Use for database performance and migration review.
docker-best-practices
Optimized Dockerfiles with multi-stage builds and security hardening. Use for container setup and docker-compose.
fastapi-async-patterns
Async FastAPI with dependency injection and service patterns. Use for building type-safe API endpoints.
frontend-analyzer
Analyze React components for design tokens and accessibility. Use for extracting typography, colors, and layout patterns.
handoff
Generate session handoff documents for work continuation. Use when transitioning between sessions.
init-deep
Generate hierarchical AGENTS.md files per directory. Use for context-specific instructions throughout projects.
internet-search
Web research with structured APIs and source hierarchy. Use for documentation lookup and technical answers.
interview
Interview users to convert rough ideas into structured specs. Use before starting non-trivial features.
mcp-security
MCP security hardening — credential leakage prevention, input sanitization, and tool access control. Use for reviewing agent MCP configurations.
mcp-server-development
Build MCP servers with Python FastMCP and TypeScript SDK — tools, resources, prompts, and transport configuration.
metis-gap-analysis
Pre-plan gap analysis for hidden intentions and edge cases. Use before delivering plans to catch missing elements.
nextjs-seo-optimization
SEO optimization for Next.js with metadata and Open Graph. Use for search ranking and social sharing.
orchestration-workflow
Practical step-by-step walkthrough for orchestrating features end-to-end using the multi-agent system, from planning through deployment
prompt-improver
Improve prompts using best practices for clarity, specificity, and structure. Use for optimizing AI agent and bot instructions.
quality-gate
Quality gate enforcement — TDD, lint, type-check, test, build checks before any commit or PR
rag-pipelines
RAG pipeline design — chunking, embeddings, retrieval strategies, evaluation, and demo patterns.
remote-sensing-analysis
Remote sensing pipeline with optical/SAR processing and ML classification. Use for satellite imagery analysis.
security-audit-pro
Security audit with SAST, SCA, containers, SBOM, PII detection. Use for comprehensive security reviews.
session-goal
Pin session objectives to prevent scope creep. Use for alignment across long multi-agent sessions.
simplify
Behavior-preserving code simplification to reduce complexity while keeping outputs, side effects, and APIs unchanged.
task-system
File-backed task management with dependencies and parallel execution. Use for complex work with 3+ interdependent tasks.
tdd-with-agents
TDD enforcement with RED→GREEN→REFACTOR cycle and advanced testing patterns. Use for test-driven development across all layers.
test-architecture
Advanced testing with E2E, load, mutation, and contract tests. Use for production-ready test coverage beyond unit tests.
file-prompts
Load prompts from external files with path expansion. Use for version-controlled prompts outside config.
memory-bank
Memory bank rules, structure, and optimization — complete guide to Pantheon memory management.
plan-architecture
Plan feature architecture with component breakdown, data flow, and dependency mapping. Use before implementation to define contracts between layers.
streaming-patterns
Implement SSE, WebSockets, LLM token streaming, and real-time broadcasting in FastAPI.
token-audit
Audit a repository for token waste — find redundant context files, measure baseline, recommend optimizations
visual-review-pipeline
Automated visual review pipeline — Playwright screenshots, self-analysis, fix loop, escalation. Used by Aphrodite for UI verification.
wisdom-accumulation
Extract learnings between implementation waves. Use to share conventions and gotchas across phases.