38,381 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.
Search and install AI assets from TokRepo — the open registry for skills, prompts, MCP configs, scripts, and workflows. Use when the user asks to find, search, discover, or install AI tools, MCP servers, Claude skills, cursor rules, prompts, or workflows.
Act as a technical partner for planning, dispatching, following, verifying, and explaining local Codex engineering work through the hermes-codex CLI. Use for implementation tasks where Codex should do the coding; do not use as a general orchestrator or for unrelated shell work.
Bridge selected questions and long coding/debugging subtasks to Doubao (豆包), ByteDance's AI assistant. Use when the user wants to forward a problem to Doubao, include environment context, wait for Doubao's real response, and use that response downstream.
Claude Code package for routing work to non-Claude models: flat one-shot dispatch and dependency-ordered Workflow DAGs over repo-installed codex/kimi/opencode/grok/qwen transport shims.
★not rated 5 22d agoA
tokens not measured
originalMIT
Guide for creating effective skills. Use when: (1) Creating a new skill from scratch (2) Updating or improving an existing skill (3) Learning skill design best practices (4) Packaging skills for distribution (5) Understanding skill structure (SKILL.md, scripts, references, assets).
Drive a Claude Code worker running in another tmux session. Use when the user wants you to be the "orchestrator" / supervisor / planner that delegates coding work to a separate Claude instance and only monitors progress. Triggers include phrases like "be the orchestrator", "the worker is in session X", "drive the…
Artful Making skills for vibe coders. 16 skills across the Shape-to-Stage flow cycle — shape your spec, validate your premise, brief it, stage it clean. The mirror never goes dark.
★not rated 5 3mo agoA
tokens not measured
originalMIT
A workflow that lets Claude and the Codex command-line tool share coding work. Claude writes a brief, Codex runs code in the background, and Claude is called back to review it.
AI codes fast. Raven enforces Discipline — Strategic Thinking, Scalable Structure, Security at Source. A plan attacked from three angles before any edit, approved by you; every prompt routed to the right one of 61 specialists, never silently; and local guards that block secrets, vulnerable libraries, and edits until…
★not rated 5 17d agoA
tokens not measured
originalMIT
An autonomous dev team in a folder. Nine agents (PM, QA, senior/junior Dev, Sweep, Reflect, Ops, Architect, Communication) build, test, ship, watch, and explain software through ticket state (Linear or the bundled local hub). 1.0 workspace model: Backlog-first intake gated by PM, sensitive-work design tier, one team…
★not rated 5 16d agoA
tokens not measured
originalMIT
VibeHarness — AI vibe coding framework for non-developers. AI acts as a senior developer handling planning, design, development, and testing. All rules are also defined in CLAUDE.md. Applies when starting a new project/feature, or continuing work on a project with docs/biz/, Progress.md, or PROJECTRULES.md.
Delegate bounded terminal implementation, cleanup, analysis, or explicitly safe finite-wave work to Claude Code while Codex retains planning, architecture, scope, review, integration, verification, and acceptance. Use when the user or host rules require Claude CLI execution, including isolated worktrees or an…
Configure or extend a multi-bot Discord setup for Claude Code, where each project directory is bridged to its own dedicated Discord bot. Use when the user wants to (a) add a new Discord bot for a new project, (b) initially set up the per-project Discord architecture, (c) pair a bot when the official /discord:access…
Continuous-learning meta-skill: identifies skill gaps in the current session's work and creates new skills to fill them. Adapted from blader/Claudeception (MIT) with marketplace-plugin packaging and dmaynor-skills-marketplace conventions. Use when: (1) you just developed a methodology that should outlive the current…
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode…
A skill for creating, updating, or reviewing an AGENTS.md file. AGENTS.md is a project note that gives coding agents lasting context about the codebase and its conventions.
Audits Claude Code project setup and provides score with recommendations. Use when user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code configuration.
★not rated 5 9mo agoA41 tokens
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: