Proof · real run

One command. 2h 45m hands-off. Approved — receipt included.

The other proofs on this site are recorded or golden demos, and say so. This one is not: a real feature of Orcho's own engine, planned, implemented, reviewed, repaired and accepted in a single run at full spend — by Orcho. Below is the receipt the run printed. Trimmed for length; every number unedited.

2h 45m hands-off, from one command to approved

7 × 5 review × repair rounds, converged to 0 active findings

1 P1 caught at plan validation, fixed on record

$116.67 API-equivalent · ~95% of input was cache reads

────────────────────────────────────────────────────────────
[DONE] Pipeline complete
────────────────────────────────────────────────────────────
  ✓ plan=ok | validate_plan=ok | implement=ok
    | review_changes=ok | repair_changes=ok | final_acceptance=ok
  • Run:   20260704_163427
  • Task:  Feature: compressed line-by-line summary grammar
           for "--output summary"
  • Evidence
  •   Tasks: 3 planned · 3 completed · 0 failed · 0 incomplete
  •   Release: approved
  •   Review findings: 1 (P1=1) | resolved: 1 (P1=1) | active: 0
  •   Run findings: 4 — attestation: 3 resolved · handoff: 1 resolved
  •   Open risks: none
  •   Scope expansion risk: 14 files flagged — unverified · no-explanation
  • Verification gates:
  ↳   pre-final auto-run: 5 ran / 5 pass
  ↳   blocking (require): broad-non-e2e, verification-unit, cli-sdk-unit
  ↳   warning (warn): env-provenance, lint — shipping allowed by policy
  • Agent advice: calls=1 · applied_retries=1 · api-equiv $0.09
  • Usage: 109,878,715 tokens (in=109,414,287 out=464,428)
           Time: 2h 45m | API-equiv: ~$116.67 | Rounds: 5
  • Usage by phase:
  ↳   plan               0.87M tok  attempts=2  $2.00
  ↳   validate_plan      0.14M tok  attempts=2  $0.42
  ↳   implement         78.1M tok   attempts=2  $74.67  (96% cache-read)
  ↳   review_changes    12.1M tok   attempts=7  $12.83  (91% cache-read)
  ↳   repair_changes    18.1M tok   attempts=5  $25.95  (96% cache-read)
  ↳   final_acceptance   0.60M tok              $0.81
  • Sessions: 8 — Claude implements (claude-opus-4-8),
    Codex reviews (gpt-5.5); reviewer peak context 69%

The run's own final output. The feature it shipped is, fittingly, the compressed summary grammar for this very receipt surface.

Run 20260704_163427 (2026-07-04): a feature of Orcho's own CLI, shipped to the public orcho-core repository through Orcho itself. The receipt is trimmed for length, local paths are removed, and the task title is translated from the operator's working language. Every number is unedited.

What to look at

The reviewer is never the author: a Claude worker implements, a Codex worker reviews. Seven review rounds and five repair rounds converge to zero active findings — the loop is control flow, not ceremony.
The engine reports on its own agents: 14 files the worker touched but never declared are flagged in the receipt, even though release was approved. Scope honesty survives success.
$116.67 is API-equivalent, not a bill: 99.6% of tokens are input, and ~95% of that input is cache reads. Cost is attributed per phase and per subtask, so you can see exactly where the spend lives.
Mid-run, the engine's advisor pushed one retry on its own — api-equivalent nine cents — and the stuck attempt resolved without a human touching the run.

The same run, annotated (docs)Cost accounting (docs)Proof hub Next proof: false-ready