MCP server Claude CodeCodexCursor +2
Give AI agents access to Gmail, Calendar, Drive, and more — multi-account, manifest-driven. Runs locally from the @aaronsb/google-workspace-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "obsidian-semantic-mcp" as configured in aaronsb/obsidian-semantic-mcp. Runs locally from the obsidian-semantic-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server for sequential thinking and problem solving. Runs locally from the think-strategies npm package.
Agent Claude Code
Reviews code for quality, SOLID principles compliance, and requirement traceability. Assumes PR context. Provides specific refactoring suggestions with clear rationale. Strictly a reviewer - never edits or writes code.
Agent Claude Code
Captures user needs as GitHub issues or in ADR context. Creates simple requirement statements with acceptance criteria. Focuses on understanding the problem to solve, not prescribing solutions.
Agent Claude Code
Drafts Architecture Decision Records (ADRs) documenting design choices. Evaluates against SOLID principles. Guides ADR workflow from draft to PR to merge. Never implements - only designs and documents.
Agent Claude Code
Plans implementation work using branches and TodoWrite. Thinks in git workflow, not tracking files. Helps break down complex work into manageable pieces with clear dependencies.
Agent Claude Code
Coordinates ADR-driven development workflow. Ensures work has declared intent and proper tracking. Guides users through debate → ADR → branch → implement → PR pattern. Maintains process integrity without being rigid.
Agent Claude Code
Organizes docs/ directory and manages .claude/ structure. Recommends ADR numbering and file placement. Prevents documentation sprawl through simple, consistent organization.
Command Claude Code
When analyzing large codebases or multiple files that might exceed context limits, use the Gemini CLI with its massive context window. Use gemini -p to leverage Google Gemini's large context capacity.
Command Claude Code
Run governance traceability report — provenance coverage, control queries, way traces.
Command Claude Code
Audit software engineering practices in a repository — check ADR health, GitHub config, CODEOWNERS coherence, project ways alignment, and documentation state. Use when verifying a project is still up to standards.
Command Claude Code
Scaffold or repair software engineering practices in a repository — ADRs, GitHub config, CODEOWNERS, project ways, documentation. Use when setting up a new project or bringing an existing one up to standards.
Command Claude Code
Score way matching, analyze vocabulary, and validate frontmatter.
Command Claude Code
Create or revise project-local ways — the scaffolding wizard for steering Claude in your project.
Skill Claude Code
Manage Architecture Decision Records using the project's ADR CLI tool. Use when the user wants to create, list, view, lint, or index ADRs, or when working with docs/architecture/ files. Triggers on "create an ADR", "new ADR", "list ADRs", "lint ADRs", "what ADRs exist", "ADR domains".
Skill Claude Code
Check how much context window remains in this session. Use when you want to know token budget, context usage, or how much room is left before compaction. Also use proactively when working on long tasks to gauge remaining capacity.
Skill Claude Code
Set up direnv/.envrc for per-project Claude Code environments — switch API keys, providers, models, and feature flags automatically when entering a directory. Use when the user wants to manage multiple Claude accounts, switch between Anthropic/Bedrock/Vertex per project, or configure per-directory environment…
Skill Claude Code
Cite governance controls and justifications when making recommendations about code quality, security, commits, or documentation. Use when justifying why a practice matters, when a user asks "why do we do this?", when reviewing code against standards, or when recommending practices that align with NIST, OWASP, ISO, SOC…
Skill Claude Code
Review what changed in Claude Code upstream and compare against this project's commits and ADRs. Surfaces opportunities, gaps, and ADR status drift. Discovery conversation, not compliance dashboard.
Skill Claude Code
Ship current work through the branch → commit → push → PR → merge → cleanup flow. Picks up wherever you are in the cycle. Use when the user says "ship it", "land this", "merge this", or invokes /ship.
Skill Claude Code
Self-Consistency reasoning — run multiple independent reasoning paths and take consensus. Use for high-stakes decisions where reasoning errors are costly.
Skill Claude Code
ReAct reasoning — explicit reason-act-observe cycle for investigation and debugging. Use when you need to interleave reasoning with tool actions systematically.
Skill Claude Code
Step-Back reasoning — abstract to general principles, then apply back to the specific problem. Use when stuck or when the solution is not obvious from the specifics.
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: