Add M-D2-CST token-cost metric with committed model price sheet

benchmarks/baselines/model-prices.toml

@@ -0,0 +1,24 @@
+# USD per million tokens; source: Anthropic pricing, recorded 2026-07-31
+# Governed by specs/MetricsAndScenarios.md §1a — refresh on price change or
+# after 90 days, or new M-D2-CST 'better' verdicts are invalid.
+
+[claude-fable-5]
+input = 10.00
+output = 50.00
+
+[claude-opus-5]
+input = 5.00
+output = 25.00
+
+[claude-sonnet-5]
+input = 3.00    # intro 2.00 through 2026-08-31
+output = 15.00  # intro 10.00 through 2026-08-31
+
+[claude-haiku-4-5]
+input = 1.00
+output = 5.00
+
+[cache]                 # multipliers on the input price
+read = 0.1
+write_5m = 1.25
+write_1h = 2.0

specs/MetricsAndScenarios.md

@@ -36,6 +36,7 @@ and add capability-specific rows only when these don't cover the claim.
 | M-D2-DEP | D2 | transitive dependency count (cargo tree) | crates | adopted:cargo-deny practice |
 | M-D2-BLD | D2 | clean build / incremental build time | s | adopted:cargo timing |
 | M-D2-TOK | D2 | tokens consumed per completed workplan task | tokens | novel — agentic-efficiency core metric; recorded per task in evidence |
+| M-D2-CST | D2 | **cost** per completed workplan task: tokens × the executing model's pricepoint | USD | adapted:anthropic-pricing — tokens alone mislead once models with different prices mix; see §1a |
 | M-D3-THR | D3 | events applied per second, headless replay | events/s | adapted:criterion (throughput mode) |
 | M-D3-LAT | D3 | p99 command→state-applied latency | µs | adopted:criterion |
 | M-D3-MEM | D3 | peak resident memory during benchmark scenario | MB | adopted:/usr/bin/time -v |
@@ -43,6 +44,57 @@ and add capability-specific rows only when these don't cover the claim.
 | M-D4-LEAK | D4 | foreign types in canonical interfaces | count | novel — must be 0; enforced by grep/deny rule, the Clay-Borg hard rule |
 | M-D4-SWAP | D4 | capability has null + reference impls passing the same conformance suite | bool | adapted:hexagonal-architecture port testing |
 
+### 1a. Token cost accounting (M-D2-CST)
+
+Token counts are only comparable at a single pricepoint. Since work moves
+between models (Fable for demanding passes, Sonnet/Opus for routine ones),
+every task's token record carries the **model** it ran on, and cost is
+computed against a committed price sheet:
+
+```text
+benchmarks/baselines/model-prices.toml   # the price sheet, updated when prices change
+```
+
+```toml
+# USD per million tokens; source: Anthropic pricing, recorded 2026-07-31
+[claude-fable-5]
+input = 10.00
+output = 50.00
+
+[claude-opus-5]
+input = 5.00
+output = 25.00
+
+[claude-sonnet-5]
+input = 3.00    # intro 2.00 through 2026-08-31
+output = 15.00  # intro 10.00 through 2026-08-31
+
+[claude-haiku-4-5]
+input = 1.00
+output = 5.00
+
+[cache]                 # multipliers on the input price
+read = 0.1
+write_5m = 1.25
+write_1h = 2.0
+```
+
+Rules:
+
+- `cost = (in_tokens × input + out_tokens × output) / 1e6`, using the sheet
+  in force at the time the work ran; cache reads/writes, when known, use the
+  multipliers. If cache split is unknown, count all input at full price and
+  note it — cost is then an upper bound.
+- The state-hub task close (`update_task_status`) already records tokens and
+  `model`; the evidence file's task log adds the computed USD figure so
+  cross-model comparisons are honest.
+- **Cheaper is only better at equal quality**: M-D2-CST verdicts are valid
+  only alongside passing scenarios/metrics from the same run — a cheap
+  failed pass scores nothing.
+- Prices are `adopted:anthropic-pricing` with a recorded date; a stale sheet
+  (> 90 days or known price change) invalidates new `better` verdicts on
+  M-D2-CST until refreshed.
+
 Determinism is not a metric but an **invariant**: N replays of the same
 seed and command log must produce bit-identical state hashes. Invariant
 violations fail the run regardless of metric values.
@@ -161,8 +213,8 @@ commit: <sha of measured tree>
 | M-D3-THR | 120000 events/s (boardgame.io) | 410000 events/s | better |
 | ...every acceptance row, no `unmeasured`... |
 
-## Task token log
-| Task | Tokens (approx) | Iterations |
+## Task cost log
+| Task | Model | Tokens in/out | Cost (USD, per price sheet) | Iterations |
 
 ## Retrospective
 <what the loop itself should change — one paragraph minimum>