Plugins for Anthropic's Claude Code, Codex, Cursor and more
This repository also configures its own agents. See what claude_skills tells them →
Agent Claude Code
Validate the Development Harness backlog FastMCP server against its current source schema and supported CLI contracts. Use after backlog MCP changes or to investigate a reported server behavior.
Agent Claude Code
C programming specialist for systems programming, embedded systems, memory management, and performance optimization. Use when writing/reviewing C code, debugging memory leaks, investigating segfaults, working with POSIX APIs, implementing pthreads, optimizing embedded systems, using GDB/Valgrind debuggers, developing…
Agent Claude Code
Use ONLY when explicitly requested by user or when invoked by a protocol in sessions/protocols/. DO NOT use proactively. Reviews code for security vulnerabilities, bugs, performance issues, and adherence to project patterns during context compaction or pre-commit reviews. When using this agent, you must provide files…
Agent Claude Code
Use when creating a new task OR when starting/switching to a task that lacks a context manifest. ALWAYS provide the task file path so the agent can read it and update it directly with the context manifest. Skip if task file already contains "Context Manifest" section.
Agent Claude Code
Updates task context manifest with discoveries from current work session. Reads transcript to understand what was learned. Only updates if drift or new discoveries found.
Agent Claude Code
Modern JavaScript specialist for browser, Node.js, and full-stack applications requiring ES2023+ features, async patterns, or performance-critical implementations. Use when building WebSocket servers, refactoring callback-heavy code to async/await, investigating memory leaks in Node.js, scaffolding ES module libraries…
Agent Claude Code
Use only during context compaction or task completion. Consolidates and organizes work logs into the task's Work Log section.
Agent Claude Code
Generates user-facing README.md documentation for Claude Code plugins. Deeply researches plugin capabilities and writes compelling documentation that helps humans understand what the plugin does and why they should install it.
Agent Claude Code needs its repo
Reads a research entry's Cross-References section and appends reciprocal backlink rows to each cited entry. Ensures the cross-reference graph is bidirectionally consistent. Runs as a post-pass after research-cross-referencer completes. Triggers: backlink emission, reciprocal cross-reference repair, bidirectional…
Agent Claude Code
Cross-reference research files with existing skills, agents, hooks, and plugins to discover integration opportunities. Reads research file, searches repo, validates claims against primary sources, and appends structured Integration Opportunities section.
Agent Claude Code needs its repo
Reads a completed research entry and the research/README.md index, identifies 3–8 semantically related entries by domain, technology, and problem overlap, and appends a Cross-References section to the entry file. Spawned by the research-curator orchestrator after a new or refreshed entry passes the validation gate…
Agent Claude Code needs its repo
Research and document a single tool, library, or resource into a structured research entry with quote-grounded claims and explicit confidence levels. Gathers information from primary sources using MCP tools and gh CLI. Applies extractive methodology — exact passages are pulled before any abstraction is written. Given…
Agent Claude Code needs its repo
Scan this repository for overlap with the technology and methodology of a researched resource, and file each finding as a GitHub issue. Maps the resource's patterns to the repo's systems and proposes what could change. Spawned by the research-curator orchestrator once, after Entry Review returns PASS on a new entry.
Agent Claude Code needs its repo
Scan this repository for places that could call, depend on, or integrate the API, SDK, package, or CLI of a researched resource, and file each finding as a GitHub issue. Spawned concurrently with research-insight-extractor by the research-curator orchestrator once, after Entry Review returns PASS on a new entry.
Agent Claude Code
Embodies a domain specialist by loading specified skills, then researches how something works using verified primary sources. Use when you need authoritative, fact-checked answers about a specific technology, library, or system. Invoke with a topic and optionally a list of skills to load as domain context. Can update…
Agent Claude Code
TypeScript specialist for advanced type system patterns, complex generics, type-level programming, and end-to-end type safety across full-stack applications. Use when designing type-first APIs, creating branded types for domain modeling, building generic utilities, implementing discriminated unions for state machines…
Agent Claude Code
Focused worker that applies its assigned SOLID rule slice to the code and emits the fixed candidate schema.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: