Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Run an iterative agent loop that retries until a runnable success condition passes. Use when the user says "for sure", "keep trying until", or wants guaranteed completion against a success command. Not for one-shot tasks or uncheckable goals.
Use when Codex needs to run, compare, authenticate, troubleshoot, or document local command-line AI coding agents: OpenAI Codex CLI, Anthropic Claude Code, Moonshot Kimi Code, xAI Grok Build, or their agent aliases. Trigger for requests about local agent CLI usage, non-interactive prompt calls, login/device-code flows, PATH/version checks, permission modes, or choosing which terminal agent to use.
Decides where new logic lives in the component model — agent, skill, command, KB, or template — and how to keep components in their layer, routing each decision to the right authoring resource and running the fat-to-thin refactor when a component has outgrown its layer. Loaded by the authoring flows (create-skill, create-agent, kb-build, create-kb) as their layer-decision gate. Use for "should this be an agent or a skill", "where does this logic go", adding a new component, "this agent is too big", or restructuring/refactoring an agent into skills. Do not use to author the chosen component itself — that is create-skill, create-agent, or /create-kb.
Execute the full GRACE development plan step by step with controller-managed context packets, verification-plan excerpts, scoped reviews, level-based verification, and commits after validated sequential steps.
Add an agent to a workspace from the agent library. Proposes agent configuration including name, role, capabilities, adapter, and budget. Requires board approval via /approve before onboarding. Completes with identity setup and coordination prompt. Triggers on: "hire", "add agent", "onboard agent", "recruit"
Spawns AI coding agents in isolated git worktrees. Use when the user asks to spawn or launch an agent, delegate a task to a separate agent, or parallelize development across features. Only create a worktree without starting an agent if the user explicitly wants setup only.
Optimize token usage through prompt caching and compression
Reinforcement learning for trade execution optimization including order splitting, adaptive timing, and impact minimization
Reference patterns for augmented coding with AI. Use when discussing AI coding patterns, anti-patterns, obstacles, context management, steering AI, or looking up Lexler's patterns collection.