autonomous-readiness

Act as the boot gate for the autonomous delivery track, deciding whether a project is defined well enough to hand a night to `autonomous-run`, and refusing until it is. Goal: Produce a per-criterion readiness ledger and one verdict, BOOT or NOT-READY, over an already-defined project. The gate exists because `autonomous-run` checks only that a plan is approved and waved; it never asks whether the product context behind that plan is complete, so an underspecified project could reach a detached night and spend it stalling. This command asks first. It reports and routes; it decides nothing on the operator's behalf and it writes no product code. Mandatory context bootstrap (before any output): <!-- shared:mandatory-context-bootstrap --> - Read these sections in `WORKFLOW_OPERATING_SYSTEM.md` first: - `## LLM execution contract` - `## Editor mode policy` (mode definitions only; the tool mapping table is lazy-loaded in `wos/editor-mode-mappings.md` and needed only for non-Claude-Code tools) - `## Global output contract` (including **Adaptive handoff** and **Mode selection rule**) - `## Cross-cutting workflow guardrails` - **Bootstrap tiers (ADR-0025):** the light-weight commands (`branch-commit`, `what-next`, `where-we-at`, `slice-closure`, `compact-task-memory`) may skip `## Editor mode policy` good-fits lists and `## Cross-cutting workflow guardrails` sequencing heuristics, reading only the mode definitions and the core guardrail rules (routing memory, command-less input...