Add refactor-scout agent — read-only technical-debt surveyor for source code

The janitor's source-code sibling: surveys existing code (not a diff) for smells,
dead code, duplication, and over-complexity, prioritizes by churn × complexity, and
recommends a disposition (refactor/delete/defer/accept) per finding designed to feed
/triage. Test-net status and risk-to-change are first-class so a refactor is only
recommended when behavior preservation can be proven. Read-only; the risky auto-apply
half is deliberately deferred and gated. ROADMAP item 11.

AGENTS.md

@@ -20,8 +20,8 @@ file added under `adapters/` is live immediately — no per-file linking:
   `/handoff`, `/full-eval`, `/capture`, `/triage`, `/roundup`, `/new-project`, `/design`,
   `/adjudicate`).
 - `~/.claude/agents` → `adapters/claude/agents/` — global subagents (reviewer, evaluator,
-  security-auditor, doc-auditor, exerciser, researcher, janitor, portability-checker,
-  start9-spec-checker, design-checker, onboarding-tester).
+  security-auditor, doc-auditor, exerciser, researcher, janitor, refactor-scout,
+  portability-checker, start9-spec-checker, design-checker, onboarding-tester).
 - `~/.claude/CLAUDE.md` → `how-i-work.md` — my universal preferences, loaded every session.
   (Distinct from this repo's *root* `CLAUDE.md`, which → `AGENTS.md`: same filename, different
   scopes — global preferences vs. this repo's orientation.)
@@ -89,9 +89,18 @@ should carry this so any vendor's agent surfaces pending items at session start:
 ## Current state
 
 - **Fleet built and live** — commands `/capture /triage /roundup /new-project /handoff /retrofit
-  /full-eval /design /adjudicate`; subagents incl. `design-checker` + `onboarding-tester`
-  (substance in `guides/`, thin wrappers in `adapters/claude/`, symlinked into `~/.claude`).
-  Dogfoods its own standard. Latest `/roundup`: `STATUS.md` 2026-06-16.
+  /full-eval /design /adjudicate`; subagents incl. `design-checker`, `onboarding-tester` +
+  `refactor-scout` (substance in `guides/`, thin wrappers in `adapters/claude/`, symlinked into
+  `~/.claude`). Dogfoods its own standard. Latest `/roundup`: `STATUS.md` 2026-06-16.
+- **`refactor-scout` shipped this session (ROADMAP item 11).** The janitor's source-code
+  sibling: read-only technical-debt surveyor that finds code smells, dead code, duplication, and
+  over-complexity in *existing* code (not a diff), prioritizes by churn × complexity, leans on the
+  repo's own analyzers, and recommends a **disposition** per finding (refactor / delete / defer /
+  accept) designed to feed `/triage`. Test-net status + risk-to-change are first-class so a refactor
+  is only ever recommended when behavior preservation can be proven. **Untested on a real repo** —
+  the first run should sanity-check that it stays opinionated/tiered (≤~12 findings, not a dump) and
+  honest about test coverage. The risky auto-apply half is deliberately **not built** (deferred +
+  gated — see item 11). Good first targets: recap, keysat.
 - **`/adjudicate` shipped this session (ROADMAP item 10).** Debates parked P2/P3 backlog to
   DROP/DO/ESCALATE verdicts; recommend-only v1, autonomy gated by blast radius, ROADMAP-only.
   **Untested on a real backlog** — the first run should eyeball the judge's drop-bias before
@@ -107,10 +116,11 @@ should carry this so any vendor's agent surfaces pending items at session start:
   notes promoted to `guides/design.md` (`176eebe`). The "confirm export internals + tune Phase-C"
   open item is **closed**. Residual is per-project execution (ten31-database mobile build, being
   scoped in that repo — not standards work).
-- **Next steps:** (1) first real `/adjudicate` run on keysat/recap to calibrate the drop-bias
-  (item 10); (2) Stage-1 `onboarding-tester` harness in a keysat session (item 9); (3) cross-repo
-  quality-gate standard + `/harden` (item 1); (4) non-git-folder sweep under `~/Projects` (item 6
-  residual).
+- **Next steps:** (1) first real `refactor-scout` run on recap/keysat to calibrate the tiering +
+  test-net honesty (item 11); (2) first real `/adjudicate` run on keysat/recap to calibrate the
+  drop-bias (item 10); (3) Stage-1 `onboarding-tester` harness in a keysat session (item 9);
+  (4) cross-repo quality-gate standard + `/harden` (item 1); (5) non-git-folder sweep under
+  `~/Projects` (item 6 residual).
 - Queued in `INBOX.md` for other repos' `/triage`: keysat design cleanup (P2) + onboarding Path-2
   (P3); `ten31-transcripts` mini-retrofit; `ten31-database` networking/icon/intake; (standards)
   operator-onboarding agent (P3).