codex-claude-code-config
View on GitHubClaude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development
A configuration system for Claude Code, Codex, and other coding agents: architectural principles, Python enforcement hooks, installable skills, and rules for multi-agent orchestration, context handoff, and agent security. Drop-in kits for global or project-local install.
Use Cases
Bootstrap a new project with verified agent rules and hooksEnforce safety guards against destructive commands and secret leaksCoordinate multi-agent and parallel-session work with lock files and mailboxesManage persistent context and handoffs across long coding sessionsOrganize reusable agent skills into installable packsAdd supply-chain and prompt-injection defenses to coding agentsGate agent 'done' claims behind durable proof artifactsRun automated read-change-test loops to improve prompts and skillsSet up cross-harness rules for Claude and Codex in one repoDetect stale docs and broken file references via session hooks
Built With
- Language
- Python
- Frameworks
- Claude Code · OpenAI Codex · MCP · Claude Code Plugins · AGENTS.md
Tags
claude-code · codex · agent-harness · hooks · skills · multi-agent · context-management · prompt-engineering · guardrails · agent-security · workflow-patterns · agents-md · configuration-kit · mcp · coding-agents · dev-workflow