docs: token ergonomics -- runtime routing/budgets/caches and the development-side tooling

One page, two halves with a Mermaid diagram each. A: the plane's token economy (one Model per Task with a metered usd/calls budget, attribution table, credentials only in the start request, repo-facts and content-addressed reuse, replay at $0, triage-hunt-tie-break order, prefix-cache prompt order) with every cost quoted from plane-increment-1/2.json, the injection-slice and harvest records, and an honest not-yet list (no token budget in ax, triage applied not run, k and contrast fixed outside experiments). B: the development-side measurement (tool I/O 85.5%, previously 90%) and the benchmarks/dev remedies: read_guard hook, bulk_read portal, token_report, plus the practices. Linked from the nav, index, memory-and-detection and the README docs list.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

docs/memory-and-detection.md

@@ -141,7 +141,8 @@ Record: `benchmarks/measurements/2026-10-01-decision-engine-injection-slice/reco
 only). Family **injection**; memory of 724 static examples from all families; input profile v1;
 framework priors off; out-of-repository evaluation (compile split never evaluated, outer grouped
 5-fold, calibration cross-fitted, operating points nested); 95% repository-cluster bootstrap
-intervals.
+intervals. The slice's spend ($0.003215 per candidate at evaluation, k = 5, and its replay at
+$0) is on [Token ergonomics](token-ergonomics.md#measured-costs).
 
 | Measure | Value | What it means |
 | --- | --- | --- |