docs(harness): add route/flywheel command guidance, ADR-286, publish status

- .claude/commands/route.md and flywheel.md -- the two CLI subcommands
  added alongside darwin/router/flywheel wiring never got matching
  guidance files (unlike doctor/review-diff), so they weren't fully
  wired into the harness's own MCP tool listing. Added, following the
  existing pattern.
- CLAUDE.md: note the crate + harness are both published now (crates.io
  v0.3.1, npm v0.1.0).
- New ADR-286 documenting the harness's MetaHarness scaffold + the
  darwin/router/flywheel wiring decision, following the ADR-182/ADR-285
  precedent (every harness in this repo gets one).
- docs/adr/README.md: index rows for ADR-286 and the crate's ADR
  (287 -- see the next commit for the renumbering-from-283 story).

harness/wifi-densepose-sar/.claude/commands/flywheel.md

@@ -0,0 +1,10 @@
+---
+description: "Run the SYNTHETIC @metaharness/flywheel self-improvement demo and report the lift curve."
+---
+
+Run the propose → evaluate → gate → promote loop and report what it found.
+
+1. Run `npm run build` first if `dist/flywheel.js` doesn't exist yet.
+2. Run `wifi-densepose-sar-harness flywheel [generations]` (default 3 if omitted).
+3. Report each generation's `primary` score and `delta`, the total promotions, and whether `verifyReplayBundle` passed.
+4. State plainly: this run's `dataSource` is `SYNTHETIC` — the proposer and evaluator are deterministic stand-ins (see `src/flywheel.ts`'s honesty note), not a real model call or a real coding-task benchmark. Do not report its numbers as if they reflect real harness improvement.

harness/wifi-densepose-sar/.claude/commands/route.md

@@ -0,0 +1,10 @@
+---
+description: "Route a 4-axis task embedding to the cost-optimal model tier via @metaharness/router."
+---
+
+Route one query to the cheapest model tier predicted to clear the quality bar.
+
+1. Run `npm run build` first if `dist/router.js` doesn't exist yet.
+2. Run `wifi-densepose-sar-harness route <physicsExplanation> <codeReview> <numericalDebugging> <docWriting>` — four 0..1 numbers scoring how much the query looks like each of those four shapes (see `src/router.ts` for the axis definitions).
+3. Report the picked tier (`cheap-tier` or `frontier-tier`), its predicted quality, and whether it cleared the 0.8 quality bar.
+4. Remind the user: the labelled examples behind this decision are illustrative seed data (see `src/router.ts`'s honesty note), not measured eval logs — the routing mechanism is real, the specific pick isn't backed by production data yet.

harness/wifi-densepose-sar/CLAUDE.md

@@ -1,6 +1,6 @@
 # wifi-densepose-sar-harness
 
-Harness for wifi-densepose-sar
+Harness for [wifi-densepose-sar](https://crates.io/crates/wifi-densepose-sar) (ADR-287) — the coherent wideband RF tomography research crate this harness assists development on. Both are published: the crate on crates.io, this harness itself as [`wifi-densepose-sar-harness`](https://www.npmjs.com/package/wifi-densepose-sar-harness) on npm.
 
 > Advanced Coding harness · domain: `software-engineering`. Generated with [create-agent-harness](https://github.com/ruvnet/agent-harness-generator).
 
@@ -25,6 +25,8 @@ Harness for wifi-densepose-sar
 
 ## Commands
 
+Each command below has a matching `.claude/commands/<name>.md` guidance file — the MCP tool listing (`mcp__wifi-densepose-sar-harness__*`) is derived from these, so a new CLI subcommand isn't fully wired up until it has one too.
+
 - `doctor` — Health-check the harness: kernel load, MCP wiring, memory backend, host adapter.
 - `review-diff` — Review the current working diff for correctness, security, and reuse.
 - `route <e0> <e1> <e2> <e3>` — cost-optimal model routing via `@metaharness/router` (needs `npm run build` first).