hoyt-harness/davinci-mcp-professional
Command Claude Code
Complete a security review of the pending changes on the current branch.
2,487 tagged mcp, measured the same way as everything else here.
Browse within: model-context-protocol 263claude-code-plugin 152ai-tools 147skills 114Multi-Agent 79open-source 74knowledge-graph 65agent-memory 64google-apis 63google-workspace 63plugin 56go 49ai-assistant 48autotask 46
hoyt-harness/davinci-mcp-professional
Command Claude Code
Complete a security review of the pending changes on the current branch.
Command Claude Code
Break complex tasks into trackable subtasks for clarity and progress monitoring.
Command Claude Code
Propose a new change - create it and generate all artifacts in one step.
Command Claude Code
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
Command Claude CodeCursor
Scan the codebase for structural improvements and execute them safely.
Command Claude Code
Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them.
eduardocornelsen/full-funnel-ai-analytics
Command Claude Code
Read dashboards/goldenmetrics.json → windowed90d.attributionbychannel and windowed90d.channelperformance; copy exact values — never recalculate (CLAUDE.md §14).
Command Claude Code
When you learn something valuable (from debugging, implementing, or discussion), use this command to update the relevant code-spec documents.
Command Claude Code
A language-agnostic debugging interface for AI agents.
Command Claude Code
Help create a Conventional Commit following the specification (https://www.conventionalcommits.org/en/v1.0.0/).
Command Claude Code
You are stress-testing a specific claim by researching the strongest possible counter-argument with real evidence. Read CLAUDE.md for sprint context and claims.json for existing claims.
Command Claude Code
Create or update the feature specification from a natural language feature description.
rails-hyperdrive/rails-hyperdrive
Command Claude Code
A fixture command gated on a gem the test bundle never resolves.
Command Claude Code
Generate a complete PRP for general feature implementation with thorough research. Ensure context is passed to the AI agent to enable self-validation and iterative refinement. Read the feature file first to understand what needs to be created, how the examples provided help, and any other considerations.
ben-rogerson/git-worktree-toolbox
Command Claude Code
Analyze the project and create a list of features that seem unfinished, aren’t being used at all or partially and categorize them.
Command Claude Code
Execute the implementation planning workflow using the plan template to generate design artifacts.
Command Claude Code
Refresh the managed Spec Kit section in coding agent context file(s).
Command Claude Code
One command to sync with the mesh — set your summary, check messages, see peers, and check locks. The daily standup for AI agents.
SkyShannonProver/shannon-prover
Command Claude Code
Prove an EasyCrypt lemma with Shannon Prover.
Command Claude Code
Project-scoped slash commands. Type / in a Claude Code session and the command's body becomes the agent's marching orders for that turn.
staticroostermedia-arch/engram
Command Claude Code
Parse a /loop input (or equivalent) per the official Grok /loop spec, call native schedulercreate directly (bare XML, never via usetool), record the schedule in Engram (quicktrace + relate to consciousness goal/tile/process), enforce sub-agent governance + subvisor, confirm per spec or scar on failure. One narrow…
Command Claude CodeOpenCode
Learn from the latest completed task using ACE post-run feedback (gated; used by auto-hook and manual fallback).
Command Claude Code
Full PR review with blast-radius, suggested questions, and surprising-connections check.
Command Claude Code
Create atomic implementation tickets for a Linear project based on its description.
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: