explainlisted

# /evo:explain — per-feature HTML explainer Produce a rich, interactive HTML explanation of **how a feature/subsystem works and how the loops collectively built it**. The default unit of explanation is the **feature** (campaign/subsystem — e.g. token-telemetry, fleet-width, queue-integrity), aggregating ALL its contributing cycles across batches: one feature = many lanes/cycles = the complete idea. Per-lane or per-batch framing is the fallback when the user asks for a specific cycle range or batch story. Each feature page has two movements: first **how it works today** (architecture, data flow end to end, with diagrams and real example data), then **how it got built** (the contributing cycles in order, what each added, which incident or root cause motivated it, including instructive failures). Output goes to `docs/explain/<feature-slug>.html` plus a shared `docs/explain/index.html` (feature table + contributing-cycle map + the deep pipeline background, written once). Repo writes land ONLY at batch/wave-safe boundaries via the gated commit path — stage in the session scratchpad until the landing window. ## Step 1 — Gather per-lane data (this repo's sources) - **Lane ↔ cycle mapping**: the newest loop log (`.evolve/loop-resume-*.log`) prefixes every line with `[<task-id>]`; worktree strings `cycle-<lane-hash>-N` inside those lines give cycle numbers. One task may map to several cycles. - **Verdicts**: `"FinalVerdict"` lines in the loop log — dedup by distinct cycle, NOT by