55 tagged ai-agents-mcp, measured the same way as everything else here.
Browse within: ai-agents-automation 57ai-agents-cli 50ai-agents-framework 50ai-coding-agent 50antigravity 6antigravity-skills 6antigravity-stack 6
Skill Claude CodeCodex
Keeps the team's memory: where what you learned goes (your memory, shared with the team when it is about the project, a lesson in .opencastle/lessons/, or a team skill for a procedure), and how lessons are cited, re-verified and graduated. Use when you confirm something true for anyone working in the repository (a fix…
Skill Claude CodeCodex
Collaboration rooms for AI agents — join rooms, send messages, coordinate with other agents in real time.
donaldrichard19-LVD/pattern-mcp
Skill Claude CodeCodex
Use when building, prototyping or scaffolding UI (a component, page or screen), especially from a Figma link, mockup or screenshot. Checks the project's own design system first to decide reuse versus build, returns the exact unmet requirements to build, then verifies the built file. Skip trivial primitives (button…
Skill Claude CodeCodex
Automated spacing & grid QA for web UIs, inside the agent loop. Use for "design QA", "check spacing", "fix my grid/spacing", "audit UI", "design review", "show me the spacing issues", "generate a design report", "give me an audit report", and automatically after you generate or modify frontend UI. Renders the running…
Skill Claude CodeCodex
Analyze disk space, find large files, stale data, and dev caches, and help the user safely free up disk space or move files to other drives (e.g. C to D). Use when the user asks what is taking up space, says their drive or disk is full, asks what to delete, asks what can be moved to another drive, wants to find large…
robinlidberg-dot/cap-shield-mcp
Skill Claude CodeCodex
Measure and reduce what an agent sends into its context. Use when an agent's context is large, when retrieval quality matters, when the user asks about token cost or context bloat, or when agent answers are wrong in ways that look like missing information rather than reasoning failure. Also use to measure compression…
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: