Persistent vector memory and semantic code search for Claude Code agents via ruvector
Index codebase for semantic search. Use when user says "index my code", "build search index", "update embeddings", "re-index project", or wants to enable semantic code search.
Record a learning, mistake, or pattern for future sessions. Use when user says "remember this", "save this pattern", "record this mistake", "learn from this", "don't forget X", or wants to persist an insight.
Browse and search stored memories and learnings. Use when user says "show memories", "what do we know about X", "list learnings", "browse reflexions", or wants to view stored agent knowledge.
Search codebase by meaning using vector similarity. Use when user says "find code that does X", "search for implementations of Y", "semantic search", "find similar functions", or "where is X implemented".
Install ruvector and initialize vector storage. Use when user says "set up ruvector", "install vector search", "enable semantic search", "initialize ruvector", or wants persistent agent memory for a project.
Store, retrieve, and flush agent learnings across sessions. Use when an agent needs to record a mistake and its fix, retrieve past learnings for a similar task, check what patterns have been successful, or flush pending updates from the queue. Also use when user says "remember this", "what did we learn about X", "record this mistake", or "flush pending updates".
Find code by meaning rather than keyword. Use when an agent needs to search for implementations of a concept, similar patterns, or related functionality across the codebase. Also use when user says "find similar code", "search by concept", "where is X implemented", or "find code that does Y".
Agent learning patterns and quality guidelines. Use when commands or agents need to determine when and how to record learnings, apply quality gates, or retrieve past knowledge using ranked retrieval.
Standard pattern for querying ruvector institutional memory before acting. Use when authoring new agents or commands that should query past patterns, findings, or solutions before executing.
ruvector workflow patterns and conventions reference. Use when commands or agents need ruvector context, MCP tool naming, current tool schemas, or error handling patterns.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Personal Claude Code plugin marketplace — 14 plugins for Git workflows, code review, CI, research, testing, documentation, code editing, and security remediation.
22.22.0 or later and below 25.0.08.0.0 or laterAdd the marketplace, then install individual plugins:
/plugin marketplace add KingInYellows/yellow-plugins
/plugin install gt-workflow@yellow-plugins
| Plugin | Description | Components |
|---|---|---|
gt-workflow | Graphite-native workflow commands for stacked PRs, smart commits, sync, and stack navigation | 6 commands, 2 hooks, 1 MCP |
yellow-browser-test | Autonomous web app testing with agent-browser — auto-discovery, structured flows, and bug reporting | 3 agents, 4 commands, 2 skills |
yellow-chatprd | ChatPRD MCP integration with document management and Linear bridging | 4 agents, 6 commands, 1 skill, 1 MCP |
yellow-ci | CI failure diagnosis, workflow linting, and runner health management for self-hosted GitHub Actions runners | 4 agents, 8 commands, 2 skills, 1 hook |
yellow-core | Dev toolkit with review agents, research agents, and workflow commands for TS/Py/Rust/Go | 13 agents, 7 commands, 4 skills, 1 MCP |
yellow-debt | Technical debt audit and remediation with parallel scanner agents for AI-generated code patterns | 7 agents, 6 commands, 1 skill, 1 hook |
yellow-devin | Devin.AI V3 API integration — delegate tasks, manage sessions, research codebases via DeepWiki | 1 agent, 9 commands, 1 skill, 2 MCPs |
yellow-docs | Documentation audit, generation, and Mermaid diagram creation for any repository | 3 agents, 5 commands, 1 skill |
yellow-linear | Linear MCP integration with PM workflows for issues, projects, initiatives, cycles, and documents | 3 agents, 9 commands, 1 skill, 1 MCP |
yellow-morph | Intelligent code editing and search via Morph Fast Apply and WarpGrep | 2 commands, 1 MCP |
yellow-research | Deep research with Perplexity, Tavily, EXA, Parallel Task, and ast-grep MCPs | 2 agents, 4 commands, 1 skill, 5 MCPs |
yellow-review | Multi-agent PR review with adaptive agent selection, parallel comment resolution, and stack review | 7 agents, 4 commands, 1 skill |
yellow-ruvector | Persistent vector memory and semantic code search for Claude Code agents via ruvector | 2 agents, 6 commands, 3 skills, 5 hooks, 1 MCP |
yellow-semgrep | Semgrep security finding remediation — fetch, fix, and verify "to fix" findings from the Semgrep platform | 2 agents, 5 commands, 1 skill, 1 MCP |
Nine plugins connect to MCP servers. Authentication requirements vary by server.
npx claudepluginhub kinginyellows/yellow-plugins --plugin yellow-ruvectorDev toolkit with review agents, research agents, and workflow commands for TypeScript, Python, Rust, and Go
CI failure diagnosis, workflow linting, and runner health management for self-hosted GitHub Actions runners
Technical debt audit and remediation with parallel scanner agents. Use when you need to assess codebase health, identify AI-generated debt patterns, prioritize findings, and systematically remediate technical debt.
Graphite-native workflow commands for stacked PR development. Provides smart commit-and-submit with parallel audit agents, stack planning, sync, and navigation — all through the gt CLI.
OpenAI Codex CLI wrapper with review, rescue, and analysis agents for workflow integration
Persistent memory system for AI coding sessions — cross-tool memory sharing with 6-dimensional hybrid search
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 8 coding-agent harnesses, content-addressed Fjall + LanceDB.
Optimized file search, semantic indexing, and persistent memory for Claude Code — with optional sync to a self-hosted web dashboard
OpenLTM — Long-Term Memory for AI coding agents: semantic search, context injection, session learning
Personal Claude Code + Codex dev stack: security hooks, AI-first code conventions, /security-review, /repo-map, /stack-check, portable statusline. Designed to complement other skills-based plugins, not replace them.
Local-first memory server — hybrid BM25+vector search, vault management, lint, and launchd lifecycle for project knowledge.