81,896 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Enhanced Telegram channel for Claude Code — drop-in replacement with all media types, voice transcription, session management, and more. Manage pairing, allowlists, and policy via /telegram:access.
★not rated 1 8mo agoA
tokens not measured
originalMIT
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
Claude Code skills and agents for Home Assistant development — custom integrations (Python), Lovelace cards (TypeScript/JavaScript), blueprints / automations (YAML), and ESPHome / add-on work.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Read a project and propose the skills and agents it actually needs. outfit infers what your repo IS, then drafts tailored Claude Code skills/agents you pick from — grounded in real evidence, never generic.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Opinionated, gated workflow for solo development with Claude: conversate, brainstorm, refine, breakdown, spec, sprint-plan, work, and review epics, stories, and tasks on a file-based board, plus independent debugging and code review, with a persistent, Obsidian-linked knowledge brain.
★not rated 1 4mo agoA
tokens not measured
originalMIT
A skill that collects recent news from RSS feeds about hackers, artificial intelligence, security, and technology, then categorises and summarises it in Traditional Chinese. RSS is a format websites use to publish updates.
Zero-dependency sound notifications for Claude Code. Plays audible alerts via PermissionRequest and Stop hooks — know when Claude needs approval or has finished, without watching the terminal. macOS / Linux / Windows.
★not rated 1 14d agoA
tokens not measured
originalMIT
Manage a backchannel room. Start, join, check status, set the share policy, or leave a shared, E2E-encrypted session with another AI coding session. Use when the user asks to start, join, check, or leave a backchannel, or to share context with a teammate's session.
Clean up raw video clips before editing: cut silence, transcribe subtitles in any language (auto-detected: English, Spanish, Mandarin, …), normalize speed, and stitch clips in filename order — outputs clean clips + .srt ready to drop into any editor. Includes a /video-prep skill plus helpers for filler-word removal…
★not rated 1
changed 1mo agoA
tokens not measured
originalMIT
A tool for checking the quality of scanned PDF files. It looks for missing or misordered pages, incorrect rotation, cropped content, and resolution problems, then reports the results in a table.
★not rated 1
changed 2mo agoA
tokens not measured
originalMIT
A set of working rules for Claude Code, Anthropic’s coding assistant, aimed at keeping long-running development work on track. It checks destructive actions, grounds work in evidence, and avoids claims that cannot be supported.
Automatic Makefile target discovery with permission-aware execution. Loads your Makefile into Claude's context so it understands project workflows, classifies targets at runtime, and enforces read/write/danger permission levels.
★not rated 1 7mo agoA
tokens not measured
originalMIT
Turn AI curiosity into a working plan at a 25 to 150 person company. Four skills an operator runs in sequence or standalone: inventory the tool stack and find where AI fits, survey employees to surface the AI use already happening, build a prompt cookbook for your actual vertical, and assemble an internal enablement…
Open a review topic and AI agents (Claude, Codex) debate it round after round -- design, attack, rebuttal -- fully hands-free until they deliver a reasoned decision.md. Multi-topic priority queue with a hardened unattended coordinator; human approval only for code changes. Windows + (beta) macOS/Linux, git and non-git.
★not rated 1 4mo 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: