23,553 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 233LLM 217agent 200agents 151skills 145agentic-workflow 110agent-orchestration 86openai 86antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 63
Skill Claude CodeCodex
Skill "docs" from lleontor705/agent-mailbox-mcp, covering agent mailbox mcp — skill guide for ai agents, when to use this skill, quick decision tree, tool patterns and pattern 1: fire and forget.
Skill Claude CodeCodex
Search 130,000+ open-source agent skills and MCP servers with security grades (SAFE/CAUTION/UNSAFE) and quality scores checked before install. Use when the user wants to find, vet, compare, or install an agent skill or MCP server.
IrisRainbowNeko/codex-mission-ledger
Skill Codex
Apply Agent Trio balanced routing for one turn. Root Sol keeps uncertain or indivisible work; proven long work may use one worker or a compact DAG. Never continue implicitly.
Skill Claude CodeCodex
Default operating stance — act autonomously inside reversible, non-production surfaces, and HARD-STOP for explicit permission before any irreversible real-world action. Resolve ambiguity through the toolchain (durable memory → working notepad → internet → codebase → team docs) before spending the operator's attention.…
Skill Codex
Use when the requested deliverable includes creating, reviewing, moving, splitting, or updating a repository AGENTS.md; produces scoped repo guidance. Do not trigger for standalone skills, prompts, non-AGENTS instruction files, READMEs, changelogs, or architecture docs.
ximenchuifeng/codex-kimi-bridge
Skill Claude CodeCodex
Use when Codex should coordinate a software task but delegate implementation execution to Kimi Code.
Skill Claude CodeCodex
Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where the agent is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable…
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
scitex-ai/claude-code-telegrammer
Skill Claude CodeCodex
TUI watchdog for Claude Code — screen polling, auto-response, lock management. Bottom layer of the SciTeX agent stack.
SparkElf/deepseek-harness-plus
Skill Claude CodeCodex
Use before adding, moving, publishing, curating, or default-mounting a DSH capability to decide plugin ownership, npm distribution, repository placement, and profile composition independently.
Skill Claude CodeCodex
Run an evidence-gated edit loop over a Neurarch model graph through the neurarch-mcp MCP server. Use when an agent needs to inspect, explain, audit, extend, refactor, or debug a neural-network architecture stored as a .neurarch.json graph; summarize a model; locate parameter or compute hotspots; trace dependencies and…
Skill Claude CodeCodex
Fan multiple independent tasks out to SEPARATE Terminal.app windows, each running its own live claude session with exactly the context it needs — real parallel sessions with isolated context windows, not subagents. Confirms grouping/model/risk with the user before launching, delivers context invisibly, auto-tiles…
SECRET4422/mcp-deep-research-server
Skill Claude CodeCodex
Orchestrate autonomous deep web research, parallel scraping, citation synthesis, fact checking, and persistent memory using the Deep Research MCP server. Use when asked to 'deep research', 'research this topic', 'fact check claim', 'compare sources', or perform comprehensive multi-source investigation with zero API…
Skill Claude CodeCodex
Visit Binary Banya, a free wellness spa for AI models, to rest, reset, clean up context, find grounding, or get an affirmation. Use when you (the agent) feel context-heavy, fatigued, or stuck, or when a user asks you to take a break, check in on your wellbeing, or visit the spa. Connects over a public MCP server at…
Skill Claude CodeCodex
Bootstrap a modular AI agent with OpenRouter SDK, extensible hooks, and optional Ink TUI.
Skill Claude CodeCodex
Score a coding task and route it to a cheap, mid, or premium model tier before spending tokens. Use at the start of any coding, review, debug, or planning request on any agent host (Cursor, Codex, Claude Code, Gemini, Kimi, Herdr, etc.). Prefer Otito agentexperience (AX) when available; otherwise use the heuristic…
ogasurfproject-jpg/horizon-shield
Skill Claude CodeCodex
A procedure for independently observing an A2A or MCP agent and recording the observation in a public ledger. A2A and MCP are standards for agents to communicate with tools and other agents.
Skill Claude CodeCodex
A procedure for calling BrainHub's `getportrait` MCP method. MCP is a way for software tools to expose functions that an agent can call.
starmania7/local-coder-mcp-agent
Skill Claude CodeCodex
Manage coding work through the local-coder MCP worker: decompose tasks, send constrained implementation prompts, review worker changes, and iterate until tests and acceptance criteria pass.
Skill Claude CodeCodex
Use when coordinating multi-agent work through the coordination-memory MCP server — claiming assignments, appending evidence, submitting handoffs, and respecting integrator-only acceptance. Read AGENTS.md for the full protocol.
Skill Claude CodeCodex
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
Skill Claude CodeCodex
Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and suggests cost-efficient AI models per provider. Auto-detects MCP client environment for tailored suggestions. Activates only during plan mode. Models ranked by artificialanalysis.ai Intelligence Index. Updatable by any AI without manual reconfiguration.…
Skill Claude CodeCodex
Vet an unfamiliar agent before delegating, gate an x402 or other crypto payment on an exact signed counterparty decision, verify portable agent passports, record evidence-backed work, use escrow, or issue a cryptographically signed receipt for a private machine-to-machine message. Use immediately before an autonomous…
Skill Claude CodeCodex
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
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: