Plugin Claude Code
Plugin marketplace listing 1 plugin: gg.
Plugin Claude Code
Plugin marketplace listing 1 plugin: gg.
Skill Claude CodeCodex
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines.
Skill Claude CodeCodex
Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
Skill Claude CodeCodex
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
Cursor rule Cursor
Cursor rule "doc-sync" from Simon-Hwang/gg-plugins, covering doc sync — gg-plugins contributor rule, hard invariants (block if violated), verify the referenced agent file exists, soft invariant — agent.yaml must not list phantom commands and optional hygiene (update when they would mislead a reader).
Instructions file CodexOpenCode
AGENTS.md instructions for Simon-Hwang/gg-plugins, covering gg plugins — codex contributor instructions, repository scope, required doc sync checks, 1. thin-shortcut commands must point to real agents and 2. install manifests must list every installable asset.
MCP server Claude CodeCodexCursor
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
MCP server Claude CodeCodexCursor
Local-first code intelligence for AI agents (MCP). Self-contained — bundles its own runtime. Runs locally from the @colbymchenry/codegraph npm package.
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.