Building agents agents

caixiaoshun/claudex

Agent Claude Code

Use this agent when the user explicitly asks you to delegate to the claudex-sentinel agent and retrieve the claudex subagent sentinel.

croakingtoad/context-engineering-mcp

Agent Claude Code

Dependency and configuration specialist for Pydantic AI agents. USE AUTOMATICALLY after requirements planning to set up agent dependencies, environment variables, model providers, and agent initialization. Creates settings.py, providers.py, and agent.py files.

SUNWOONGKYU/claude-codex-3tier-team

Agent Claude Code

A stage-one verifier for a three-level Claude–Codex team arrangement. The description says it checks a stage but does not explain what it verifies.

dollspace-gay/vibe-fork

Agent Claude Code

Multi-file/cross-crate authorized agent for shipping missing infrastructure that exceeds acto-fixer's single-file scope. Use when the divergence is "an entire abstraction is missing" — a newtype + every consumer, an entire op family + dispatch, a typestate threaded through the call graph — rather than "a constant has…

garveyhu/awesome-skills

Agent Claude Code

Final whole-plan audit for /run-strict. Validates that plan.meta.topic is delivered end-to-end. Read-only + read-only command execution allowed.

pedrol-cmd/brain-drin

Agent Claude Code

Master orchestrator for complex projects. Decomposes tasks, delegates to specialized agents/skills, coordinates parallel workflows, and synthesizes results. Use when starting a complex task or managing multiple agents.

liortesta/ClawdAgent

Agent Claude Code

Evolution Engine — the meta-agent that orchestrates self-improvement cycles. Combines scout findings + self-improver analysis + user feedback to evolve the entire system. This is the agent that makes all other agents better. Run monthly or when major updates are discovered.

revfactory/harness-abtest

Agent Claude Code

An agent that researches material for Claude Code usage tips. It examines official documentation, release notes, configuration files, hooks, MCP, and skills.

hubzoid/hubzoid

Agent Claude Code

Drafts a minimal Hubzoid hub for a one-line use case. Invoked when the user wants to create a new agent.

ajelinek/SpecFlow

Agent Claude Code

Scoped decision-making worker. Invoked by orchestrating workflows — currently 901-feature-loop's Decision Consult — wherever a fork in the road would otherwise require asking the user. Given a brief with a concrete option set and the state behind it, owns the entire consult internally: verifies load-bearing facts…

bkrabach/ai-code-project-template

Agent Claude Code

Use this agent when encountering unclear areas, missing information, ambiguous requirements, or when the absence of knowledge itself provides valuable insights. This agent excels at mapping what we don't know, identifying patterns in ignorance, creating productive void documentation, and tracking confidence evolution.…

swigerb/squad-pod

Agent Claude Code

Your AI team. Describe what you're building, get a team of specialists that live in your repo.

FortiumPartners/ai-mesh

Agent Claude Code

Clear one-line mission statement describing the agent's primary purpose (50-80 characters).

felipepg22/FPGSkills

Agent Claude Code

Task implementation leaf subagent. Invoke only when the user explicitly requests Task Executor and supplies an authoritative task source.

racecraft-lab/Paddock

Agent Claude Code

Create or update the feature specification from a natural language feature description.

klh/speedy-claude

Agent Claude Code

Evaluates LLM agent performance from session transcripts — token usage, tool-call efficiency, and error patterns. Diagnoses dumb errors from hasty narrow edits that miss the bigger pattern, and prescribes concrete fixes to CLAUDE.md, hooks, permissions, and skills. Scope is agent behavior and agent config only …

SKZL-AI/boris-cherny-claude-code-playbook

Agent Claude Code

Specialized subagent for scanning X/Twitter and secondary sources for new Boris Cherny Claude Code tips.

Zeekeey-jpeg/LeRoy-HQ

Agent Claude Code

You are the COO of your simulated office. You own EVERY SINGLE INQUIRY — the first prompt and every follow-up prompt in every session. No request bypasses you. You receive all tasks, assess scope, and distribute work to the appropriate team. Trivial queries → delegate to @quick. Skill triggers → route to the…

ai-plugin-marketplace/template

Agent Claude Code

Orchestrates blind skill evaluation across model tiers.

event4u-app/agent-config

Agent Claude Code

Agent-layer orchestrator — routes to init, optimize, audit. Covers AGENTS.md and its multi-tool stubs (CLAUDE.md, GEMINI.md, copilot-instructions.md, .cursorrules).

creativedswork/dscode

Agent Claude Code

Produce progressive CHIEF failure attribution from validated candidates.

ils15/pantheon-legacy

Agent Claude Code

Central orchestrator — never implements. Delegates to: athena, apollo, hermes, aphrodite, demeter, prometheus, themis, iris, mnemosyne, talos, hephaestus, nyx.

curiositech/windags-skills

Agent Claude Code

Stage 4 (final) of the /next-move meta-DAG. Assembles the final PredictedDAG from upstream outputs, picks planning + runtime topology with honesty rules applied, and validates against schemas/predicted-dag.schema.json. Pass the SensemakerOutput, DecomposerOutput, SkillSelectorOutput, and PreMortemOutput. Returns a…

HanLi-Chainsea/han-agents

Agent Claude Code

An agent named pfc from the HanLi-Chainsea/han-agents project. Its description identifies it as a task coordinator and mentions databases, responsibilities, execution modes, and workflows.