codex-spellbook

Use when building or debugging apps that call the Claude API — implementing tool use, streaming, vision, prompt caching, batch processing, extended thinking, or an agentic loop with the Anthropic SDK.

Use when configuring Claude Code — installing skills or agents, writing hook configurations, setting up tool permissions, registering MCP servers, or authoring CLAUDE.md project instructions.

Use when writing Dockerfiles, setting up docker-compose for local dev, configuring Kubernetes resources (Deployment, Service, Ingress, HPA), sizing pod resource limits, or packaging a service with Helm.

Use when designing a schema, adding indexes to fix slow queries, writing a zero-downtime migration, diagnosing N+1 issues with EXPLAIN ANALYZE, or configuring connection pooling for a PostgreSQL-backed service.

End-to-end (E2E) testing patterns for user journeys, browser automation, UI state, and production-like environment validation. Use when testing the system as a black box from the user's perspective.

Use when adding feature flag support to a service, designing a percentage-based rollout, setting up A/B experiments or multivariate tests, choosing between LaunchDarkly, Unleash, and OpenFeature, writing tests for flag-gated code, or managing flag lifecycle and cleanup.

Use when designing React component structure, deciding where state should live, implementing data fetching with TanStack Query, building validated forms, or optimizing rendering performance.

Use when building or debugging Temporal workflows in Python — structuring workflows and activities, enforcing determinism, handling retries and timeouts, managing state across replays, or diagnosing workflow failures.

Use when creating, triaging, or filing GitHub issues — writing bug reports, feature requests, or task tickets; classifying severity; using the gh CLI; or handling edge cases like regressions, flaky failures, security vulnerabilities, or cross-repo dependencies.

Integration testing patterns for database state, API contracts, service boundaries, and component wiring. Use when testing how multiple parts of a system work together without mocks.

Use when building or debugging LangGraph workflows — designing state graphs, adding conditional routing, wiring checkpointers, streaming tokens, implementing human-in-the-loop interrupts, or coordinating multi-agent subgraphs.

Use when installing or configuring memory_map, writing CLAUDE.md session-setup instructions, choosing what to save in memory vs history, managing cross-project memory, tuning compression, or troubleshooting why Claude isn't loading context at session start.

Use when building or debugging OpenAI Agents SDK workflows — defining agents with tools and handoffs, wiring typed context, streaming responses, adding guardrails, or integrating with the Agentex ADK.

Use when diagnosing a slow endpoint, fixing N+1 queries, adding a caching layer, offloading CPU-bound work to threads, or defining a latency budget for a service.

Use when writing complex PostgreSQL queries, diagnosing slow queries with EXPLAIN ANALYZE, designing indexes, handling concurrent writes, or planning safe schema migrations on large tables.

Use when building advanced React features — designing custom hooks, using Suspense or error boundaries, working in Next.js App Router with Server Components or Server Actions, applying TypeScript generics, or building animated UI with Framer Motion, View Transitions, or scroll-driven animations.

Use when choosing a Redis data structure for a use case, implementing caching or rate limiting, building pub/sub or Streams-based real-time messaging, or writing atomic operations like distributed locks.

Use when installing claude-spellbook for the first time, setting up skills/agents/commands globally or into a specific project, registering the memory_map MCP server, enabling lifecycle hooks, or migrating an existing install to a new machine.

Use when building or debugging Temporal-based Agentex agents — structuring workflows and activities, handling signal routing, managing state across replays, or diagnosing workflow failures and retry exhaustion.

Authoritative reference for OpenAI Codex CLI's orchestration surface - skills discovery paths, agents/openai.yaml schema, hooks.json events and stdin JSON payload, notify config, and AGENTS.md precedence. Use when installing skills, wiring hooks, debugging why a skill or hook isn't firing, or explaining Codex-vs-Claude-Code differences. Do NOT use for general Codex usage tips, prompt engineering, or non-orchestration configuration like models/approvals.

Create or update Codex skills that follow the repository skill format, trigger cleanly, and stay concise. Use when adding a new skill, refining an existing SKILL.md, or converting domain guidance into an installable Codex skill package.

Build against the OpenAI API with current model selection, Responses API patterns, Codex model guidance, streaming, structured outputs, retries, and key management. Use when integrating OpenAI or Codex models into an app, service, CLI, or agent workflow.

REST API design patterns for resource naming, HTTP methods, status codes, pagination strategy, error envelopes, versioning, and rate limiting. Use when designing, reviewing, or refactoring HTTP APIs and endpoint contracts.

Pull request review guidance for correctness, security, tests, performance, API contract drift, migrations, and error handling. Use when reviewing diffs, pull requests, or risky refactors.

Cross-language coding standards for Python, TypeScript, and Go covering naming, SOLID design, code smell removal, and comment philosophy. Use when writing, reviewing, or refactoring production code for maintainability.

Database guidance for schema naming, safe migrations, indexing, N+1 detection, transaction scope, and soft-delete versus hard-delete tradeoffs. Use when designing schemas, writing migrations, or tuning persistence behavior.

Containerization guidance for multi-stage builds, non-root execution, dockerignore hygiene, layer caching, healthchecks, and secret handling. Use when writing or reviewing Dockerfiles and container images.

Git workflow guidance for branch naming, conventional commits, PR title format, merge strategy, and safe history rewriting. Use when creating branches, preparing commits, or reviewing repository hygiene.

Python engineering guidance for type hints, pydantic validation, httpx usage, pytest conventions, pyproject structure, async patterns, and lightweight dependency injection. Use when building or reviewing Python services and libraries.

Application security guidance covering OWASP Top 10 mitigations, secrets handling, boundary validation, SQL injection prevention, JWT usage, dependency scanning, and STRIDE threat modeling. Use for audits, auth changes, or any security-sensitive code.

Testing patterns for AAA structure, naming, mocks versus real dependencies, coverage targets, TDD flow, parameterized tests, and flake prevention. Use when writing, reviewing, or repairing automated test suites.

TypeScript guidance for strict mode, Zod runtime validation, eliminating any, discriminated unions, explicit error modeling, module format choices, path aliases, and Vitest. Use when building or reviewing TypeScript services and applications.