Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 390,176 indexed, measured the same four ways as everything else here.
Used to query or process existing approval instances and approval tasks. Use when users mention approval to-dos, agree, pass, complete, reject, return, withdraw or cancel an instance, retrieve for reconsideration, edit approval forms, submit after filling, change handler, add sign-off node, remind, mark an approval…
Writes a phased implementation plan with parallel execution waves for a software task as a reviewable artifact with a Proceed button, while keeping the target codebase read-only: scope and non-goals, size-routed discovery (duckdb, packrat, context-indexer, rg, sem), concrete file-level changes, and per-track…
A research workflow that follows discussions on X, formerly Twitter, from an account, post, or topic and summarizes the claims, replies, criticisms, and unresolved points with sources.
Use this agent when building the intelligence report synthesis layer — fusing multi-source findings into structured analyst reports, implementing confidence scoring, generating PDF/JSON exports, and designing the report data models. Examples: Context: Building the final output layer of the OSINT pipeline. user: "Build…
Research public Xiaohongshu or Zhihu content, inspect permitted Zhihu account data, and prepare, validate, review, and optionally publish Xiaohongshu image-text or Zhihu content through existing platform tools. Use when the user explicitly requests a Xiaohongshu or Zhihu content operation; do not use for generic web…
Review an implementation plan against the current repository and its explicit dependencies, reporting evidence-backed blockers, required revisions, and optional improvements before work begins. Use when asked to review a plan or assess implementation readiness.
★not rated 2
changed 8d agoA
tokens not measured
originalMIT
Creates original editorial illustrations where a recurring mascot character performs the idea — one caught scene by default, a hand-built explainer diagram (labeled stages, a fan-out, timeline, loop, or stack) when the structure itself is the point, or a transparent character cutout (pose-only compositing asset, no…
Persistent memory for Claude across conversations. Recall and save decisions, preferences and facts in your private Kumiho workspace, review stored memories, and import reviewed memories from selected past conversations. Connect via /mcp (Cowork: Connect) after installing. Bundles the hosted Kumiho Memory MCP…
★not rated 2
changed 29d agoA
tokens not measured
originalMIT
Runs the named product delivery lifecycle for new ideas, major changes, resumption, remediation, or closure only when the user explicitly invokes /launch-pipeline or requests this named workflow.
The log your next session resumes from: decisions, dead ends, handoffs and open tasks, shared across machines, agents and people over the todox MCP server. Reminds a session to read the log first and to write it up before finishing.
★not rated 2 yesterdayA
tokens not measured
originalMIT
Unattended drain of the whole open-ticket queue from the canonical checkout: one fresh Orca worktree plus a Claude child session per ticket running /dowork then /ship, user tickets before must before nice, canonical main synced after each merge, until the queue is empty. Use for "/doall", "do all the tickets", "drain…
Bring Pine AI into your agent to handle real-world tasks and follow up on progress and results.
★not rated 2
changed 5d agoA
tokens not measured
originalMIT
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: