A snapshot: read at commit 707a04c7ce8 on 2026-10-18T00:06:01Z by majordomus 0.29.0. Nothing on this page is read again. See it live
Economics
What a coding session consumes with Majordomus and without it, from matched runs judged by the same hidden tests. Observed, counted, derived, estimated and counterfactual numbers are labelled as such. Every token figure is a reduction, 1 - treatment / control: a negative reduction means Majordomus used more tokens.
Verdict
No verified total-token-savings claim is available: no valid matched pair of live runs is recorded under methodology 1.
The publication rule is not met:
- 0 valid pair(s); the rule asks for 30
- 0 categor(ies) with at least 5 valid pairs; the rule asks for 4
- 0 repetition(s) of csv-credit-notes (baseline) in suite pilot, the least repeated; the rule asks for 3 of every task and variant
- no interval: too few valid pairs, or too few tasks among them
Headline
—Total-token reduction with Majordomus (median over valid pairs)effective_token_reduction · derived from observed · n=0
+97.9%Context selection by the compiler (not total savings)context_reduction_ratio · derived from counted · n=315
Evidence
| Suite | Kind | Evidence | Runs | Valid pairs | Control failed | Treatment failed | Both failed | Other | Detail |
|---|---|---|---|---|---|---|---|---|---|
context | context | current | 9 | 0/0 | 0 | 0 | 0 | 0 | |
pilot | live | no evidence | 0 | 0/0 | 0 | 0 | 0 | 0 |
Metrics (13)
| Metric | Value | Status | Class | n | Interval | What it is not |
|---|---|---|---|---|---|---|
| effective_token_reduction | — | not measured | derived from observed | 0 | — | not context reduction: this is everything the provider reported for the whole task, not what one mechanism selected |
| cost_reduction | — | not measured | derived from observed | 0 | — | not a bill: the harness prices usage from its own table at run time, and historical runs are never re-priced |
| tool_call_reduction | — | not measured | derived from observed | 0 | — | not a token metric |
| continuation_reduction | — | not measured | derived from observed | 0 | — | only the session that continued the work, not the whole task |
| first_request_overhead | — | not measured | derived from observed | 0 | — | not the whole overhead: what the treatment reads later because its instructions say to is in the total, not here |
| completion_rate.baseline | — | not measured | derived from observed | 0 | — | not a quality score: a run passes the gates or it does not |
| tokens_per_completed_task.baseline | — | not measured | observed | 0 | — | |
| transcript_resume_avoided.baseline | — | not measured | counterfactual from observed | 0 | — | not a saving of Majordomus: both arms start the next session fresh; this is the modelled cost of resuming a transcript instead |
| completion_rate.majordomus | — | not measured | derived from observed | 0 | — | not a quality score: a run passes the gates or it does not |
| tokens_per_completed_task.majordomus | — | not measured | observed | 0 | — | |
| transcript_resume_avoided.majordomus | — | not measured | counterfactual from observed | 0 | — | not a saving of Majordomus: both arms start the next session fresh; this is the modelled cost of resuming a transcript instead |
| context_reduction_ratio | +97.9% | measured | derived from counted | 315 | 95%: +97.9% to +98.0% | not total token savings: it says what the compiler selected from what it found relevant, not what a session consumed, and a session remains free to read anything |
| context_cost_model_error | -1.6% | measured | derived from counted | 315 | — | not a saving: it says how far the budget's unit is from counted tokens |
Segments
| Dimension | Segment | Valid pairs | Median reduction | Min | Max |
|---|
Pairs (14)
| Task | Category | Rep | Status | Control tokens | Treatment tokens | Token reduction | Reasons |
|---|---|---|---|---|---|---|---|
csv-credit-notes | regression | 1 | missing | — | — | — | the control run is not recorded |
csv-credit-notes | regression | 2 | missing | — | — | — | the control run is not recorded |
currency-czk | small-feature | 1 | missing | — | — | — | the control run is not recorded |
currency-czk | small-feature | 2 | missing | — | — | — | the control run is not recorded |
invoice-discounts | cross-module | 1 | missing | — | — | — | the control run is not recorded |
invoice-discounts | cross-module | 2 | missing | — | — | — | the control run is not recorded |
recurring-invoices | multi-session | 1 | missing | — | — | — | the control run is not recorded |
recurring-invoices | multi-session | 2 | missing | — | — | — | the control run is not recorded |
storage-v2 | schema-change | 1 | missing | — | — | — | the control run is not recorded |
storage-v2 | schema-change | 2 | missing | — | — | — | the control run is not recorded |
test-repair | test-repair | 1 | missing | — | — | — | the control run is not recorded |
test-repair | test-repair | 2 | missing | — | — | — | the control run is not recorded |
vat-rounding | bug-fix | 1 | missing | — | — | — | the control run is not recorded |
vat-rounding | bug-fix | 2 | missing | — | — | — | the control run is not recorded |
Hypotheses — stated before the evidence, not results
- long-running-work (untested): Long-running agent development work consumes 30 to 70 percent fewer tokens with Majordomus, centred near half.
- short-tasks (untested): Short isolated tasks gain less and may cost more, because the bootstrap and briefing are paid on every session.
- continuity (untested): Work that spans sessions gains the most, because a handover replaces rediscovery.