All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 436,299 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
LLM Sandbox is a lightweight and portable sandbox environment designed to run large language model (LLM) generated code in a safe and isolated mode. Runs locally from the llm-sandbox Python package. Needs 12 environment variables to run.
Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.
Run Arbor's hypothesis-tree research workflow inside Claude Code using your own model — no API key. Bundles the Arbor Agent Skill suite and registers the keyless arbor mcp tools (Idea Tree, evaluation, worktrees, guarded merges, reports).
★not rated 1.1k▲
+3 5d agoA
tokens not measured
originalApache-2.0
A framework for building a digital version of a person from conversations, social-media material, and documents. It extracts working methods, interaction patterns, memories, and personality into a reusable agent skill, with templates for different relationships.
Architect-as-orchestrator for Claude Code on any session model: it writes specs and verdicts, GPT-6 Luna (via Codex, effort max by default) does the routine typing, GPT-6 Sol (effort high by default) takes the high-complexity one-offs, every step is labelled with its model, and Fable 5.1 reviews every deliverable…
Let Claude watch a video. Downloads with yt-dlp, extracts scene-change frames with ffmpeg, runs a dense 0-10s hook microscope, pulls captions or falls back to Whisper, emits a structured report.md, and (optionally) auto-saves into your Obsidian vault.
★not rated 1.1k▲
+34 3mo agoA
tokens not measured
originalMIT
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
open-claw-skills. A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
★not rated 1.1k▲
+5 yesterdayA
tokens not measured
AGPL-3.0
Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.
Orchestrate bounded Codex, Claude Code, Agy, Kimi, or custom CLI workers to finish work with the least lead context and provider usage, following playbooks such as plan big, execute small. Use when the user asks to orchestrate, delegate, compare agents, conserve agent tokens or quota, recover a worker, report what an…
Build and edit designs directly in Figma Desktop from your terminal — render frames/components/variants, manage design tokens & variables (shadcn/Tailwind/DTCG), extract & import whole design systems, gradients, Figma Motion, and accessibility audits. Controls Figma live over a local connection, no API key.
★not rated 1.1k▲
+14 17d agoA
tokens not measured
originalMIT
Demo skill that web-fetches two Decoding AI knowledge-graph articles, has the agent itself distill them into a typed entity/relation graph, and renders an interactive dark-themed force-directed KG into one self-contained kg.html — no graph library, no CDN.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions.
Edit CapCut and JianYing (剪映) projects from Claude Code — subtitles and SRT/ASS import, timing, speed, volume, keyframes, masks, filters and effects, templates, lint --fix, render previews, and cutting long-form to shorts.
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: