Token economics
What a coding session consumes with Majordomus installed and without it, from recorded runs: matched control and treatment sessions judged by the same hidden acceptance tests, the provider's usage as it reported it, and every number labelled with its measurement class (observed, counted, derived, estimated, counterfactual). One calculator; every surface is a projection of it, and the verdict states only what the methodology's publication rule allows.
What a coding session consumes with Majordomus installed and without it, from recorded runs: matched control and treatment sessions judged by the same hidden acceptance tests, the provider's usage as it reported it, and every number labelled with its measurement class (observed, counted, derived, estimated, counterfactual). One calculator; every surface is a projection of it, and the verdict states only what the methodology's publication rule allows.
- module economics
- builtin
- behaviorally_verified
- 4 capabilities
Capabilities
Each composed in this module's file; each with its own page.
economics.checkScan the repository's hand-written prose and claim sentences for a quantity (a percentage, 'N times fewer') stated next to the economics vocabulary, and check every claim the methodology binds to a metric: a bound claim may be guaranteed only while its metric's evidence meets the binding and is current. `ok: false` names every finding.query · behaviorally_verified · majordomus_economics_check · GET /api/v1/economics/checkeconomics.explainOne metric and everything it rests on: its formula, its measurement class and what that class means, the pairs and runs behind it (including the invalid ones), excluded runs, the suites and revisions, and the commands that reproduce it. A repository that declares no methodology has no metric, and any id is answered with `present: false` and the statement why, not refused.query · behaviorally_verified · majordomus_economics_explain · GET /api/v1/economics/explaineconomics.runsThe raw facts every economics metric is computed from: each recorded run with its task, variant, repetition, model, revision, success-gate verdicts and the totals derived from its provider usage, and the path of its record.query · behaviorally_verified · majordomus_economics_runs · GET /api/v1/economics/runseconomics.summaryEvery metric of the economics benchmark with its value, measurement class, sample size, distribution and bootstrap interval; every pair of runs with its status (valid, control failed, treatment failed, incomparable, ...); results by segment; the state of each suite's evidence (current, stale, incompatible); and the one statement the publication rule allows. Context reduction and total-token reduction are separate metrics and are never merged.query · behaviorally_verified · majordomus_economics · GET /api/v1/economics