Add repeatable verification and establish fresh save checkpoint

Consolidate current readiness and existing rule decisions, preserve selective
subagents and automatic verified Git pushes, and record the efficiency pilot.
Add source-bound compact checks, private saved-game snapshots/online backups,
and bounded HTTP seat-restoration checks with 15 meaningful regressions.

At the user's explicit request, archive and clear 3,644 old local rooms and
related records while retaining schema/migrations; preserve future games from
a fresh empty baseline. Private backups and credentials are outside Git.

Validation: npm run check passes types, lint and all 4,177 offline tests.
Full report: 20260913-efficiency-check-3, 130.147 seconds; source fingerprint
344ce1d44475b0cd4ff10a915f28331cb4e2fcacbc7595636fbaa645c0568f64.
Two earlier broad attempts stopped at new type/lint errors before tests;
both were fixed. Independent review found cancellation falsely passing;
SIGINT/SIGTERM regressions and review confirm the fix. Documentation links,
example test selection, private backup integrity and empty baseline verified.
No app/build/dependency/HTTP implementation changed; no production build,
HTTP suite, browser acceptance or AI calibration claimed for this checkpoint.
The full game goal and existing release gates remain unfinished.

docs/EFFICIENCY_PILOT.md

@@ -0,0 +1,26 @@
+# Three-milestone efficiency pilot
+
+Preserve the complete game scope and required checks. Use small relevant reads,
+coherent feature batches, selective subagents and compact verification artifacts.
+Git remains mandatory: review, verify, commit, push and confirm remote success at
+each finished implementation checkpoint. Never force-push or commit credentials.
+The removed recurring automation stays removed.
+
+| Milestone | Deliverable | Measurement |
+| --- | --- | --- |
+| 1: setup | Current status, decision index, reusable checks, saved-game snapshots/backups and HTTP seat restoration | Start aggregate goal counter: 57,957,554 tokens. Latest observed pre-continuation counter: 57,986,221; partial delta 28,667 includes planning/context and is not a finished-milestone cost. Two bounded helpers: documentation and independent tooling review. Final checkpoint records actual checks. |
+| 2: core readiness batch | Remaining Basic/Advanced capabilities with rules, controls, bots and recovery together | Record start/end aggregate counters, accepted capability, focused/broad runs, reviewer effort and reopened defects. Pending material rulings remain explicit. |
+| 3: next dependency batch | Next core or connected expansion capability selected from current evidence | Repeat measurements; compare cost per accepted capability and investigate repeated work. |
+
+The aggregate counter may update only between turns. Record a confirmed endpoint
+when available rather than estimating missing usage. It includes coordination and
+conversation overhead and is not a dollar-cost meter. Different capability sizes
+limit direct comparisons; do not promise a savings percentage from this setup.
+Do not count tests alone as accepted faction or mode completion. Scripts consolidate
+existing checks; broad checks still run once source/review is stable and repeat if
+subsequent changes or failures justify them. Browser fixtures remain feature-specific;
+the reusable HTTP restoration helper does not automate browser setup or visual QA.
+
+Use [current status](CURRENT_STATUS.md), [rule decisions](RULE_DECISIONS.md) and
+[verification workflow](VERIFICATION_WORKFLOW.md) as short entry points. Historical
+logs remain references, not mandatory full-context input on every turn.