pip install signalbrain
bash demo/demo.sh

▶ 1. An agent tries to score its own claim BEFORE anyone merged it
  {"status": "refused_guard", "code": 3, "message": "... not on HEAD — score only human-merged receipts"}
  refused: unmerged claims cannot enter the ledger. No agent grades its own homework.

▶ 2. A batch of receipts measured only by tests the agent wrote itself
  ledger now holds 3 rows — every one classified: 3 "claim_kind": "invariant_pin"
  {}   (no class has ANY trust-eligible claims)
  three green results, ZERO earned trust: held-by-construction pins are recorded, never counted.

▶ 3. An honest failure
  "held": false
  the agent said 0.9 confidence. The measurement said no. That gap is the product.

▶ 4. Ten claims that actually hold
  "tooling": { "hit_rate": 1.0, "n": 10, "status": "auto-merge ELIGIBLE" }
  earned by track record, revocable by evidence. Autonomy is graduated, never granted.

flowchart LR
    A["Agent ships change<br/>+ receipt"] --> B{"human<br/>merges?"}
    B -- "no" --> R["refused — unmerged claims<br/>cannot be scored"]
    B -- "yes" --> C["sb score<br/>re-runs the receipt's<br/>own commands"]
    C --> D{"measured only by<br/>tests it wrote itself?"}
    D -- "yes" --> P["invariant_pin<br/>recorded · zero trust"]
    D -- "no" --> E{"commands<br/>pass?"}
    E -- "yes" --> H["held ✓"]
    E -- "no" --> F["held ✗<br/>recorded forever"]
    H --> L[("ledger")]
    F --> L
    P --> L
    L --> G{"last 10 high-confidence<br/>claims ≥ 95% held?"}
    G -- "yes" --> M["auto-merge ELIGIBLE<br/>earned · revocable"]
    G -- "no" --> N["GATE<br/>human review"]

    classDef good fill:#0d2b1e,stroke:#34d399,color:#a7f3d0
    classDef bad fill:#2b1214,stroke:#f87171,color:#fecaca
    classDef neutral fill:#0f172a,stroke:#475569,color:#cbd5e1
    class M,H good
    class R,F,P bad
    class A,B,C,D,E,G,L,N neutral

uvx --from "signalbrain[mcp]" sb-mcp

pip install signalbrain

# 1. Teach your agents to emit receipts (paste into CLAUDE.md / .cursorrules):
#    docs/pilot/receipt-emission.md

# 2. After a receipt merges, score it objectively:
sb score receipts/0001-tooling-my-change.md --root . --ledger .signalbrain/ledger.jsonl

# 3. Read the trust gates (exit 0 = TRUST earned, 1 = GATE):
sb gate --ledger .signalbrain/ledger.jsonl --by-class --window 10

# Or wire it into CI — see the fork-able demo's workflow:
#    https://github.com/whitestone1121-web/receipt-gate-demo

export PYTHONPATH=src:scripts
python scripts/calibration_ledger.py docs/calibration/improvement_claim_ledger.jsonl \
  --require-measured --by-class --window 10
bash scripts/calibration_score_receipt.sh docs/improvements/NNNN-name.md
pytest tests/ -q