deep-researchlisted

# ASK Deep Research Turn hard technical uncertainty into an autonomous research program. Gather and challenge evidence; do not implement source changes. ## Start Write a research brief before broad search: question, objectives and decisions enabled, in/out scope, constraints, key unknowns, initial hypotheses, expected report. Do not repeatedly ask permission when the next source follows from this brief. ## Research Program 1. Build a dynamic plan. Split independent tracks: local implementation, real fixtures/logs/captures, upstream, history, official standards/docs, and community evidence where relevant. 2. Inspect local code, tests, fixtures, configuration, Git history, issues, and PRs before interpreting external claims about local behavior. 3. Discover sources broadly, then narrow with identifiers, versions, hardware, protocol fields, and terminology learned. Prefer direct runtime evidence, reproducible tests, source, standards, and official docs. 4. Delegate independent tracks through `agent-workflows`; coordinator owns scope, evidence reconciliation, plan updates, and synthesis. Report meaningful findings at milestones, not tool noise. 5. Extract evidence, not URL lists: `Source | section | observation | interpretation | confidence | contradiction`. 6. Track each important statement as `FACT`, `OBSERVATION`, `INFERENCE`, `HYPOTHESIS`, `ASSUMPTION`, or `UNKNOWN`. Maintain hypotheses with support, contradictions, status (`OPEN`, `SUPPORTED`, `WEAKENED`, `DISPROVEN`, `