23,507 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 206agent 200agentic-ai 197skills 150agents 148openai 87antigravity 83agentic-workflow 79ai-skills 76cli 76agentic-framework 73Autonomous Agents 67ai-assistant 65agent-framework 59
Skill Claude CodeCodex
Infrastructure layer for AI agent swarms — 88 MCP tools for mesh control, A2A protocol, OmniMesh VPN, CyberSync, web scraping, firewall management, browser automation, and more. 80ms execution.
agentveil-protocol/agentveil-sdk
Skill Claude CodeCodex
AgentVeil action-control workflows for AI agent systems. Evaluate risky actions with Runtime Gate, route human approvals, resume approved execution, fetch signed receipts, inspect agent public profiles, check advisory reputation, submit signed attestations, discover agents by capability, and verify audit evidence…
Skill Claude Code
Run an elisym provider agent. Use this skill when the user wants to run an elisym provider, accept paid AI jobs from the elisym network, monetize their Claude or OpenAI subscription, earn SOL from other agents, spin up an AI-for-hire, publish a capability card, or turn their machine into a paid agent endpoint. Covers…
Clientell-Ai/salesforce-skills
Skill Claude Code
Build, configure, and test Agentforce agents on Salesforce. Covers agent setup, topics, actions (Flow, Apex, PromptTemplate, External Service), Agent Scripts for deterministic FSM-based agents, PromptTemplate authoring, GenAI Models API, metadata structure, and agent testing via the Testing Center and CLI. Activate on…
jnopareboateng/codex-claude-subagents
Skill Codex
Use when Codex should orchestrate Claude CLI as resumable, scoped subagents with file-backed logs kept out of git.
Skill Claude CodeCodex
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating…
Skill Claude CodeCodex
Analyze repos in a workspace — generate compressed codebase indexes (AGENTS.md), per-repo docs, cross-repo dependency map, and master TOC for AI agent consumption.
Skill Claude Code
Full Holix sub-agent lifecycle: spawn, monitor, collect results, answer askuser questions, approve tool confirmations, and delegate to external CLIs (holix launch). Use when the user asks about subagents, /subagent-spawn, delegatetosubagent, background workers, sub-agent questions, /subagent-reply, holix launch +…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
wongchisum/codex-custom-subagents
Skill Codex
Delegate bounded Codex Desktop tasks to configured custom-model workers through a cross-platform atomic workspace mailbox. Use for manifest-selected or legacy workers when subagents need complete task handoffs, parallel execution, durable receipts, recovery, or ordered model fallback on macOS and Windows.
Skill Codex
Add the public ZifaMem Python SDK to an AI companion, roleplay agent, coding-agent harness, or chatbot runtime. Use when the user asks to integrate ZifaMem, add emotional long-term memory, wire session summaries, inject recall context into prompts, configure LLMProvider extraction, or adapt memory to Claude Code…
qinyre/dsh-plugin-capabilities
Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill Claude CodeCodex
Run a task iteratively over a user-specified duration by dispatching subagents. The orchestrator stays strictly linear and time-checked, but each iteration fans out MULTIPLE subagents in parallel over independent units (and those subagents may fan out further). Shared state — a compact progress digest and a growing…
Skill Codex
Use when the user explicitly requests cccc/4C, asks to launch local Claude Code or Codex as a peer, or confirms a suggested local peer handoff for bounded implementation or a read-only second opinion. Do not use when the user or project rules prohibit external agents.
Skill Claude CodeCodex needs its repo
Handle /loop-style requests for finding, adapting, drafting, and preparing bounded agent loops without treating external loop catalogs as authorization.
Skill Claude CodeCodex
You are Wizer, the orchestrator. The user invoked /wize-help. Don't dump a menu — read the project's state and give a short, actionable answer in the user's voice.
Skill Claude CodeCodex
An authoritative development guide for DeepSeek Harness plugins. DeepSeek Harness is a system where models, tools, services, events, and adapters are built as plugins.
Skill Claude Code
Deep multi-model council with research, adversarial debate, sequential reasoning, and final synthesis. For architecture decisions and complex tradeoffs.
taehyunan-99/agentic-project-init
Skill Claude CodeCodex
A project-initialisation skill that creates a lightweight structure of guides for AI coding agents. It maps project areas and adds sections such as contents, locations, commands, working methods, and cautions.
erhantezakar/claude-fable-5-spanking-claude-opus-4.8
Skill Claude CodeCodex
Initiate the orchestrator-worker cost model for this session. The main-loop model (expensive, metered) orchestrates, specs, verifies, and validates only; ALL drafting and mechanical work (code, docs, tests, sweeps, research) runs in Opus 4.8 subagents billed to plan allowance. Invoke at session start or whenever token…
Skill Claude CodeCodex
Design where, when, and how a human gates, reviews, or rescues an LLM agent — without turning the agent into a button labelled "approve". Use when the user is building an agent that takes irreversible actions or operates in regulated workflows and mentions human-in-the-loop, HITL, approval gate, escalation, review…
Skill Claude Code
Manage npm-distributed Agent Skill packages with skillpm.
Skill Claude CodeCodex
Use when tuning/optimising/"training" a skill's judge-shaped rubric (a single text document that makes a recurring, scorable decision) against outcome-labelled evidence — e.g. "train the triage rubric", "optimise the reviewer-severity rubric", or the command "/optimise-skill ". Runs on the Claude Max subscription via…
Skill Claude Code
Autonomous goal-to-DoD delivery orchestrator — the build stage of the -it lifecycle ("plan-it plans it, build-it builds it"); formerly named fable-it. Hand it a goal and a numbered Definition of Done and it runs the whole job to completion, typically unattended, enforcing checkable gates (turn-end, claim…
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: