Light-ship mode / per-diff toggles for always-on adversarial + doc agents (subscription usage caps)

## Feature request: a light-ship mode (or per-diff toggles) for subscription-capped users

`/ship` currently has one ceremony level. The <50-line specialist skip is great, but three costs remain unconditional on every ship:

1. The **Claude adversarial subagent** ("always-on for every review... no configuration needed") — a fresh full-context agent even for one-line copy tweaks.
2. The **document-release pass** (+ its verifier agent).
3. The **workflow turn count** itself (~50 tool steps in /ship + ~40 in /land-and-deploy), where every >5-min CI wait expires the Anthropic prompt cache, so each wake-up re-uploads the session's full context at cache-WRITE price.

On Claude Max (weekly usage caps), measured on a real project over 7 days: ~93M input-token-equivalents, of which a one-line wording tweak shipped via /ship + /land-and-deploy cost **324 turns, 3 subagents, ~1.4M cache-write tokens**, and a lint-cleanup ship cost **528 turns, 7 subagents, ~4.6M cache-writes**. "Boil the ocean" is the right ethos when marginal cost ≈ 0, but subscription caps make the marginal cost real; today the only knobs are the global `skip_eng_review` (all-or-nothing, "not recommended") and `codex_reviews`.

**Ask (any of these would help):**
- A `light_ship_max_lines` config: below the threshold AND no user-designated risky paths, skip the adversarial + doc agents and the deep canary — keep tests, checklist review, version/changelog, PR.
- Or per-feature toggles: `adversarial_review: always|risky-only|off`, `doc_release: always|risky-only`.
- Independently: batch the long CI waits in /land-and-deploy into a single blocking script call (one model wake-up instead of one per phase) — this alone removes ~1M cache-write tokens per shipped PR for cap-limited users, with zero behavior change.

Workaround we've deployed locally (happy to share): a "two-lane" CLAUDE.md rule that routes small non-risky diffs around /ship to a native commit/push/PR flow with an inline checklist review, gated by a PreToolUse hook that deterministically re-verifies diff size + risky paths before allowing the push, plus a single-wake watcher script for the CI chain.

Start by tracing the /ship and /land-and-deploy workflows, then read the mentioned CLAUDE.md two-lane rule, PreToolUse hook, and CI watcher script. Compare the proposed light-mode or per-feature toggles and batched waits against the current global skip_eng_review and codex_reviews controls. Done means an agreed design is implemented with unchanged required checks and lower work for small, non-risky diffs.

Written by the indexing model from the issue text.