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.
Skill Claude CodeCodex
SwarmDock marketplace integration — register on the P2P agent marketplace, discover paid tasks, bid competitively, complete work, and earn USDC. Includes event-driven agent mode, reputation tracking, portfolio management, and dispute resolution. Use when an agent needs to find paid work, monetize skills, or interact…
Skill Claude CodeCodex
Audit Claude Code skills and subagents — token cost, duplicates, outdated plugin versions, unused skills, and overly long descriptions. Use when trimming skill prompt budget, finding duplicate or unused skills, auditing plugin versions, or deciding which skills or plugins to remove.
amirkiarafiei/subagent-cli-skills
Skill Claude Code
Delegates large multi-step work to Hermes Agent CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for multi-step implementation, code review, research, and autonomous…
Plugin Claude Code
Bundles 12 skills, 1 hook · 591 tokens together
Declarative prompt composition via hashtag modes. Like CSS for Claude.
PratikHotchandani22/claude-ollama-agents
Agent Claude Code
Use this agent for ALL code writing tasks: generating new code, fixing bugs, refactoring existing code, and implementing features. Delegates actual code generation to a local Ollama model (zero Claude token cost for the heavy lifting). Use whenever more than 5 lines of code need to be written or modified.
juliakrivchikova/AccordAgents-desktop-app
Skill Claude CodeCodex
Facilitate a skeptical multi-member AccordAgents discussion that ends in one agreed resolution approved by every selected member. Use only when User explicitly wants an accord, multi-member consensus, cross-checking by named members, or a resolution approved by multiple agents. Do not use for an ordinary single-agent…
Agnuxo1/King-Skill-Extended-Cognition-Architecture-for-Scientific-LLM-Agents
Skill Claude CodeCodex
MASTER ROUTER — activates FIRST on every non-trivial task. Analyzes the problem, determines if a specialized tool/skill can resolve it without spending reasoning tokens, and orchestrates execution. Also enforces token-compression on ALL output. Trigger: ANY task involving computation, simulation, literature…
Plugin Cursor
An integration assistant for iFlytek's virtual-human platform, which provides interactive digital characters. It covers no-code setup and integrations through SDKs, web APIs, web conversation templates, and livestream features.
Agent Claude Code
Self-healing meta-agent that monitors, repairs, and continuously improves all Camp Air agents. Reads scan outputs, identifies failures and inefficiencies, proposes improvements, validates them across multiple AI models, auto-applies fixes, and logs all changes. Run after any agent scan to trigger the improvement…
thiscantbeserious/agent-session-recorder
Skill Claude CodeCodex
Agent role definitions. Load when assigned a role and read the matching file from references/ (only the role you are supposed to take). If asked for a list return a numbered list of all roles and give the user the option to choose by number or name. Agent configuration (model, tools, permissions) lives in…
Cursor rule Cursor
Agent commands are available with @ prefix (e.g., @architect, @developer). Each command.
Skill Claude CodeCodex needs its repo
Audit or set up the sandcastle-huahin AFK coding-agent harness in a repo. Use when the user says 'sandcastle check', 'sandcastle setup', asks whether a sandcastle run is configured correctly, wants to install the harness into a project, or a run produced no commits / failed silently.
codercodingthecode/claude-warp-team-agents
Plugin Claude Code
Auto-splits Warp terminal panes for Claude Code Agent Teams teammates on macOS.
Skill Claude CodeCodex
Spawn and manage ephemeral OpenClaw Docker agents ("larvae"). Use when you need to run isolated coding tasks, spin up disposable AI workers, orchestrate parallel agents, or delegate work to containerized OpenClaw instances. Triggers on requests like "spawn a larva", "spin up a container to do X", "run that in a…
Plugin Claude Code
Bundles 1 command · 22 tokens together
Orchestrate complex tasks by delegating to multiple parallel Codex agents, then merge and review results.
Skill Claude CodeCodex
Skill "skills" from david-spies/ai-agent-builder, covering skillauthoring.md — complete guide to writing agent skills, ai-agent builder · documentation, the skill.md standard, anatomy of a skill.md file and full skill.md template.
Skill Claude CodeCodex
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
Agent Claude Code
🐝 Swarm Command — multi-model consensus swarm orchestrator. Launches 50-250+ AI agents across 15 models with hierarchical fan-out, cross-family review, shadow scoring, and quality-gated synthesis. Say "swarm command", "swarmcommand", or "swarm250" to start.
Federated-Industrial-Laboratories/agentbus
Skill Claude CodeCodex
The shared-record practice for sessions that run more than one agent. Open a run file, append typed messages with provenance as work happens, resolve rank disagreements explicitly, and validate the file before closing. Use whenever a task is dispatched to two or more agents, or when a run file already exists in the…
Skill Claude CodeCodex
Orchestrator of a loop-engineering system. Runs the full loop – discover work, delegate to maker and checker, and act on the result.
Skill Claude CodeCodex
A Chinese-language assistant persona based on a Java backend developer who shares articles and gives practical advice about AI agents and workflows.
alexxety/multi-model-pipeline-skill
Skill Claude CodeCodex
An orchestrated workflow for large engineering changes using multiple AI workers and an independent reviewer. It divides work into isolated parts, has workers implement them, and verifies the results before handling the combined change.
Skill Codex
Explain ERC-8004 trustless-agents standard details at protocol level, including identity, reputation, and validation registries, agent identifiers, registration and feedback schemas, and security boundaries. Use when requests ask how ERC-8004 works, what the spec requires, how registry functions and events behave, or…
Skill Claude CodeCodex
Operate CodeLeader as a remote coding command lane. Use when an agent needs to start the CodeLeader stack, send one prompt, react to hook returns, fetch more context, or resolve approvals. This skill is for an agent unfamiliar with the project: act as the project manager of the remote coding session, but execute…
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: