# 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.