caio-moliveira/workshop-agent-harness
Agent Claude Code
Revisor de código do time. Use após implementar uma fatia / antes de commitar ou abrir PR, para revisar o diff contra as regras do projeto (.claude/rules/), correção e os invariantes do produto. Verificação SOFT (LLM revisando código) — complementa o gate HARD (ruff+mypy+ pytest do hook), não o substitui. Dispare com…
caio-moliveira/workshop-agent-harness
Command Claude Code
Gera o scorecard de entrega (correção, aderência, throughput, autonomia) p/ o time e stakeholders.
caio-moliveira/workshop-agent-harness
Command Claude Code
Gate rápido de validação — ruff + mypy + pytest. Rode antes de cada commit.
caio-moliveira/workshop-agent-harness
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From caio-moliveira/workshop-agent-harness.
caio-moliveira/workshop-agent-harness
Hook Claude Code
Runs when the agent finishes a response, running an inline shell check. From caio-moliveira/workshop-agent-harness.
caio-moliveira/workshop-agent-harness
Settings file Claude Code
Agent settings declaring 2 hook events (PostToolUse, Stop) and 27 allowed tools.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and…
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Compact the current conversation into a handoff document for another agent to pick up.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Skill de entrevista que transforma o PRD (ou spec/documento de arquitetura) de um projeto num setup concreto de agent harness no diretório .claude/. Use SEMPRE que o usuário quiser planejar ou estruturar o harness de um projeto de código, montar ou andaimar o .claude/ (CLAUDE.md, rules, skills, subagents, commands…
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both…
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Create LangChain agents with createagent, define tools, and use middleware for human-in-the-loop and error handling.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy, and langgraph.json configuration.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
caio-moliveira/workshop-agent-harness
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.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, threadid, time travel, Store, and subgraph persistence modes.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
INVOKE THIS SKILL when creating, deploying, running, or operating Managed Deep Agents in LangSmith. Covers deepagents-cli, the Python and TypeScript SDKs, React useStream, REST fallbacks, MCP tools, interrupts, backends, and the managed agent file tree.
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine…
caio-moliveira/workshop-agent-harness
Skill Claude CodeCodex
Modern React UI patterns for loading states, error handling, and data fetching. Use when building UI components, handling async data, or managing UI states.