Capability-aware model routing for Codex, Copilot, Claude and provider APIs. Triggers: model routing, model selection, reasoning effort, approved fallback, cost, escalation.
Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. Triggers: prompt caching, cache_control, cache breakpoint, cache TTL, hit rate.
Sets up ai-toolkit in a project: symlinks, CLAUDE.md, intent interview. Triggers: onboard, setup project, install ai-toolkit, migrate project.
Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent, create agent, agent scaffold, specialized agent.
Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR. Persists ownership, progress and commit-bound evidence for safe resumption. Use for autonomous software delivery or finishing an interrupted…
Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
Coordinates multiple specialized agents in parallel. Triggers: orchestrate, multi-agent, parallel agents, coordinate agents.
Executes plans via fresh subagents per task with two-stage review (spec → quality). Triggers: subagent execution, execute plan, fresh agent per task, spec compliance review.