Instructions file CodexOpenCode
Instructions for a six-role multi-agent system: Coordinator, Planner, Reviewer, Executor, Evaluator, and Memory Curator. The roles divide work such as understanding requests, planning, coding, checking results, and preserving useful context.
Instructions file
A project guide for an AI-agent harness, meaning software that runs and coordinates coding or research agents. It describes skills, session hooks, multiple agents, tool connections, memory, and built-in checks, with commands for setup and verification.
Skill Claude CodeCodex
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Skill Claude CodeCodex
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
Skill Claude CodeCodex
Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
Skill Claude CodeCodex
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.
Skill Claude CodeCodex
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
Skill Claude CodeCodex
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
Skill Claude CodeCodex
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
Skill Claude CodeCodex
Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.
Skill Claude CodeCodex
Use this skill to validate the "why" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract.
Skill Claude CodeCodex
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
Skill Claude CodeCodex
Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.
Skill Claude CodeCodex
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
Skill Claude CodeCodex
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
Skill Claude CodeCodex
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
Skill Claude CodeCodex
A comprehensive verification system for Claude Code sessions.
Skill Claude CodeCodex
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.