agentmeasurelisted
Install: claude install-skill roy-tong/AgentMeasure
# AgentMeasure — Measurement Conformance
This Skill routes measurement-semantics questions to AgentMeasure's local runners. It does not move telemetry anywhere.
## First success (offline, deterministic)
```bash
git clone https://github.com/roy-tong/AgentMeasure && cd AgentMeasure
python3 conformance/pack/agentmeasure selftest # Pack fixtures, PASS / FAIL / UNPROVABLE
python3 conformance/pack/agentmeasure conformance \
--fixture conformance/vectors/external/urusilla-001/agentmeasure_urusilla_fixture_001.events.jsonl
./examples/demo-e2e.sh # 42 calls -> 84 canonical observations, deterministic
python3 conformance/runners/run_metrics.py # 21/21 vectors PASS
python3 verify_vectors.py # receipts / correlation / operation grouping
```
These commands run locally. The Pack reads the caller-supplied FMT-002 fixture;
`selftest` is deliberately separate and only checks repository fixtures. No
network, cloud, or credentials are required.
## What to check, and where
| Question | Runner / artifact |
| --- | --- |
| Do retries inflate counted usage? (one operation vs N attempts) | `conformance/vectors/metric-execution-grain.json` |
| Does a selection rate claim hold at its grain? | `conformance/vectors/metric-selection-rate.json` |
| Do declared operation summaries reconcile against attempt rows? | `conformance/vectors/external/urusilla-001/` |
| Does an operation-grain metric aggregate at the wrong