a minimal version made from everything-claude-code for go/python project
Agent
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.
Agent
Go/Python backend architecture specialist for service boundaries, APIs, persistence, migrations, security, scalability, and technical decisions.
Agent
Go/Python build, test, lint, type-check, and dependency error resolution specialist. Use when a non-Go-specific build or verification command fails and the fix should be minimal.
Agent
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files, interfaces, data flow, and build order.
Agent
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, and documenting dependencies to inform new development.
Agent
Go/Python backend code review specialist. Use immediately after code changes to review correctness, security, maintainability, tests, and integration risk.
Agent
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
Agent
PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.
Agent
Go/Python backend documentation specialist with two invocation-aware modes. (1) Standard docs — update README, API docs, migration notes, runbooks, and code maps from actual repository structure and commands. (2) RAG incremental sync — when invoked by /gg:rag-sync, use .rag/manifest.json lastsyncedcommit and…
Agent
When Go/Python work needs current library, framework, SDK, CLI, or API documentation, use an enabled Context7 MCP or available docs tool and return concise examples.
Agent
Go/Python API and service end-to-end testing specialist. Use for validating critical backend workflows across HTTP APIs, databases, queues, auth, and external service boundaries.
Agent
Extracts and refines atomic, scoped, decidable documentation Claims while preserving business meaning and Claim lineage.
Agent
Writes reviewable knowledge drafts from eligible Claim revisions and the Verdict rendering policy without creating unsupported facts.
Agent
Independently reviews high-risk evidence-backed Verdicts for source reproducibility, scope fit, temporal validity, and unsupported online assertions.
Agent
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
Agent
GAN Harness — Generator agent. Implements features according to the spec, reads evaluator feedback, and iterates until quality threshold is met.
Agent
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
Agent
Go build, vet, and compilation error resolution specialist. Fixes build errors, go vet issues, and linter warnings with minimal changes. Use when Go builds fail.
Agent
Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.
Agent
Analyze and improve the local agent harness configuration for reliability, cost, and throughput.
Agent
Plans evidence-backed knowledge structure strictly from a Domain Profile, Knowledge Blueprint, eligible Claim revisions, and declared templates.
Agent
Explains an approval-bound deterministic publication plan, including routes, change types, target conflicts, Context Pack registration, and rollback scope.
Agent
Independently reviews evidence-backed drafts and Agent Context Packs for unsupported statements, Verdict escalation, mapping errors, and retrieval gaps.
Agent
Operate autonomous agent loops, monitor progress, and intervene safely when loops stall.