Use when coordinating work in a shared repo — multi-agent or solo across sessions: collision avoidance, handoffs, verification debt, durable memory/wiki, hooks setup/debug, and repo learning before planning, editing, reviewing, or testing.
Use when an idea needs disciplined exploration before building: generate options, test worth-building, map adjacent solutions, challenge assumptions, narrow scope, or choose Build RFC / Prototype / Narrow / Park — even without saying brainstorm.
Use when browser debugging needs Chrome DevTools evidence: network, console, performance, DOM/CSS, screenshots/PDF, security, cookies/storage, or auth-gated live pages via CDP — not just opening a URL.
Use when writing or updating docs: README, API docs, runbooks, AGENTS.md, CLAUDE.md, ADRs, Diátaxis restructuring, or codebase documentation for humans or coding agents.
Use when measuring whether a change helped: ACCEPT/REVERT, keep/discard, goal→KPI contracts, eval suites, graders, held-out checks, benchmarks, or TDD failing-case-first.
Use when saving tokens with a local Ollama worker while the cloud agent keeps tools and judgment: summarize, extract, classify, translate, article digest after fetch, draft, checklist, vision caption, map-reduce, or phrases like ollama worker, local model, offload, use ollama.
Use when an agent prompt, skill, tool schema, policy, or handoff needs to get clearer, safer, easier to trigger, cheaper in context, or measurable against real behavior.
Use when a technical question or code change needs evidence before conclusions: find or locate behavior, explain systems, diagnose failures, review diffs, validate dependencies or prior art, prove dead code, plan refactors, or ship the smallest verified fix.