pantheon-legacy

Tool-agnostic search — query construction, tool selection, source trust hierarchy.

Auto-continue through todos with idle detection and safety gates. Use for multi-step orchestration.

Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references

Automated visual review pipeline — Playwright screenshots, self-analysis, fix loop, escalation. Used by Aphrodite for UI verification.

Multi-agent orchestration with model routing, category delegation, and sprint management. Use for coordinating Pantheon agents.

MCP security hardening — credential leakage prevention, input sanitization, and tool access control. Use for reviewing agent MCP configurations.

Load prompts from external files with path expansion. Use for version-controlled prompts outside config.

Plan feature architecture with component breakdown, data flow, and dependency mapping. Use before implementation to define contracts between layers.

Implement SSE, WebSockets, LLM token streaming, and real-time broadcasting in FastAPI.

Audit a repository for token waste — find redundant context files, measure baseline, recommend optimizations

Extract learnings between implementation waves. Use to share conventions and gotchas across phases.

Evaluate AI agent outputs — hallucination detection, quality scoring, behavioral testing, and CI/CD pipelines.

Observability with OpenTelemetry, metrics, and logging. Use for monitoring agents and LLM calls.

Design RESTful APIs with pagination, filtering, and OpenAPI docs. Use for FastAPI endpoint design.

Structured artifact trail for feature implementations — plans, implementations, reviews, and decisions.

Cache patterns for Redis, CDN, TTL, and invalidation. Use for architecture decisions on caching strategies.

Systematic code review with quality gates, security audit, and parallel checks. Use for structured feedback on pull requests.

Generate codebase maps with directory trees and relationships. Use for onboarding and architecture documentation.

Design conversational AI with Rasa NLU, dialogue management, and LangChain memory patterns.

Database migrations with Alembic, rollbacks, and zero-downtime deployment. Use for schema changes.

Optimize SQL queries, indexes, and identify N+1 problems. Use for database performance and migration review.

Optimized Dockerfiles with multi-stage builds and security hardening. Use for container setup and docker-compose.

Async FastAPI with dependency injection and service patterns. Use for building type-safe API endpoints.

Analyze React components for design tokens and accessibility. Use for extracting typography, colors, and layout patterns.

Generate session handoff documents for work continuation. Use when transitioning between sessions.

Generate hierarchical AGENTS.md files per directory. Use for context-specific instructions throughout projects.

Web research with structured APIs and source hierarchy. Use for documentation lookup and technical answers.

Interview users to convert rough ideas into structured specs. Use before starting non-trivial features.

Build MCP servers with Python FastMCP and TypeScript SDK — tools, resources, prompts, and transport configuration.

Pre-plan gap analysis for hidden intentions and edge cases. Use before delivering plans to catch missing elements.

SEO optimization for Next.js with metadata and Open Graph. Use for search ranking and social sharing.

Practical step-by-step walkthrough for orchestrating features end-to-end using the multi-agent system, from planning through deployment

Improve prompts using best practices for clarity, specificity, and structure. Use for optimizing AI agent and bot instructions.

Quality gate enforcement — TDD, lint, type-check, test, build checks before any commit or PR

RAG pipeline design — chunking, embeddings, retrieval strategies, evaluation, and demo patterns.

Remote sensing pipeline with optical/SAR processing and ML classification. Use for satellite imagery analysis.

Security audit with SAST, SCA, containers, SBOM, PII detection. Use for comprehensive security reviews.

Pin session objectives to prevent scope creep. Use for alignment across long multi-agent sessions.

Behavior-preserving code simplification to reduce complexity while keeping outputs, side effects, and APIs unchanged.

File-backed task management with dependencies and parallel execution. Use for complex work with 3+ interdependent tasks.