38,442 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.
Agency Swarm is a framework that allows anyone to create a collaborative swarm of agents (Agencies), each with distinct roles and capabilities. Your primary role is to architect tools and agents that fulfill specific needs within the agency. This involves.
Interactive bilingual course skill for learning loop engineering through Loopath. Use when a user wants to start, continue, install, teach, study, verify, or be quizzed on the Loopath course; when they ask for an agent-guided course on coding-agent loops, harness design, AGENTS.md, action schemas, tool use, policy…
Run, supervise, or explicitly cancel long-running, background, async, or detached processes from OpenAI Codex CLI and wake or resume the owning Codex session on process completion, without LLM/model polling while the job runs. Use when asked to run something in the background, start or stop a long build, test…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
David's built-in skills — create-agent, create-job, create-dashboard — bundled with the David VS Code extension and auto-loaded into every David-spawned agent's Claude Code session via --plugin-dir.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Aggressive token and output minimization for coding agents. Use when the user wants concise technical Spanish, minimal useful output, small patches, and strict scope control.
Use this skill when the user wants to create, scaffold, or configure a new Gemini CLI extension. It provides expert guidance on manifest structure, MCP servers, Agent Skills, and release workflows.
A voice-control rule for a gated Korean-and-English voice assistant. It defines which wake phrases start listening and how spoken replies must be formatted.
Reconcile every AI coding agent's conversations (Claude Code, Codex, Gemini, Cursor, Aider, opencode, Cline + 11 more) with git and docs into one cited ground truth, and distill durable ADR/PDR/BDR decision records.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Audits AI agent projects for security risks in prompts, tools, memory, RAG, and permissions. Use when: the user asks to review agent security, harden an agentic system, check for prompt injection risks, audit tool permissions, or secure an AI assistant before deployment. Do NOT use for: projects with no agentic…
Agent Ops is the skill of managing and coordinating multiple agents to work together effectively. It involves assigning tasks, tracking progress, resolving conflicts, and ensuring that agents collaborate smoothly to achieve shared goals.
Activate the Arcanea Orchestrator — the multi-CLI routing brain. Shows status, routes tasks to best model (claude/opencode/codex/gemini), runs plans and workflows, and delegates to sub-CLIs via Bash. Distinct from /ao (Composio session manager).
Hand your agent an entire spec and walk away: autonomous multi-sprint execution with a decision journal, checkpointed file-based state, and a scheduler that relaunches fresh sessions whenever context or usage limits hit. Works with Claude Code, Codex, Gemini CLI, and any headless agent.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Use a fresh task profile and a four-level policy to turn material ambiguity into a precise, self-contained prompt without asking the user to make technical choices the agent can investigate.
Route explicit requests from a host coding agent to one or more locally configured AI executors through Codeck, attach Markdown or other project files, moderate cross-model consultation, expose disagreements, and synthesize traceable results. Use when the user explicitly names Codeck or asks to consult, compare, or…
Delegate tasks or get a second opinion from Claude Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Claude Code, or offloading work to it. Do not use when already running inside Claude Code…
A package manager for installing and managing cognitive bases, which are add-ons that provide an AI agent with additional capabilities or instructions.
Run, inspect, resume, and stop Agent Workflow Kit workflows from Codex.
★not rated 2 1mo agoA19 tokens
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: