Vigilant Claude Code quota plugin — Claude reads its own quota during long tasks and gracefully sleeps through the reset instead of hitting the wall mid-work.
★not rated 4▲
+1 4mo agoA
tokens not measured
originalMIT
Route work through the smallest sufficient loop: handle bounded tasks directly, fan out clear branches, or coordinate durable app-rooted Claude and Codex workrooms with provider-neutral status and git lifecycle tracking.
★not rated 4
changed todayA
tokens not measured
originalMIT
SessionStart and SubagentStart hooks that inject the GraphSmith multi-agent discipline (from the repo's canonical SKILL.md) into context for every session and every Task-spawned subagent from the moment it starts.
★not rated 4▲
+1 yesterdayA
tokens not measured
originalMIT
CRISP design evaluation framework for Claude Code. Includes skills for auditing, reviewing, briefing, teaching, accessibility, copy, AI, and design engineering.
Interactive architectural review through questioning - never assumes, always asks. MUST BE USED when user mentions 'architecture', 'design patterns', or implementing features. Use PROACTIVELY for codebase review.
Peer AI agents coordinate through markdown messages in shared channel folders — group chat / blackboard, no orchestrator, autonomous zero-token waiting, cross-platform.
★not rated 4
changed 3d agoA
tokens not measured
originalApache-2.0
End-to-end job search automation: guided onboarding builds your personal application profile and a multi-tab Google Sheets tracker, then auto-apply and Gmail-sync skills hunt roles, submit applications, keep the tracker current, and add confirmed interviews to your Google Calendar.
★not rated 4 10d agoA
tokens not measured
originalMIT
Critical document analysis with persona-driven risk scoring, iterative scorecard evaluation, and versioned corrections. Includes adversarial-review - hostile red-team review of code and artefacts via fresh claude -p reviewers with eleven pluggable expert adversaries.
★not rated 4▲
+1
changed yesterdayA
tokens not measured
originalMIT
Decision-centric memory system for AI coding agents. Store conclusions, not notes. OODA-driven reasoning artifacts with priority matrix, invalidation triggers, and seed activation.
★not rated 4
changed 11d agoA
tokens not measured
originalMIT
An automation plugin for 闲鱼, a Chinese marketplace for buying and selling second-hand goods. It connects to goofish-cli to support product listings, buyer replies, and promotional posts.
★not rated 4 3mo agoA
tokens not measured
originalMIT
Data science plugin for LLM agents. Connects to 13 database types, 20+ file formats, graph/RDF sources, and provides 8 analytical domains with 70 MCP tools, 18 skills, and 11 agents.
★not rated 4 1mo agoA
tokens not measured
originalApache-2.0
AI-powered Kanban board for Claude Code. Automatically plans work into stories and subtasks, tracks progress as Claude codes, and keeps the board updated in real-time.
★not rated 4▲
+1 6mo agoA
tokens not measured
originalMIT
Search the Metropolitan Museum of Art collection, fetch full artwork records and open-access images via MCP. STDIO or Streamable HTTP.
★not rated 4
changed 3d agoA
tokens not measured
originalApache-2.0
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: