# Label check

A reader forms a model of a rule from its label before reading the body. If the label points the wrong way (ambiguous, covering only one side, or about something adjacent), that wrong model sticks. This test measures what a label actually conveys by asking agents that never see the body.

## When to run it

- Names of strict rules and constraints.
- Section headers that gate non-trivial content.
- Any label that is meant to carry the whole intent on its own, including top-level skill names.

Purely organisational headers ("Examples", "Setup") do not need it.

## Inputs

1. The candidate label.
2. One paragraph of the surrounding context, as a reader would meet it.
3. The intended meaning in one to three sentences. This stays with you; the agents never see it. If you cannot state it in three sentences, fix the body before testing the label.

## A round

Launch five subagents **in one message**, so none anchors on another. Each receives only the label and the context paragraph, never the body, and is told to commit to what the label means in one or two sentences, under 80 words, with no hedging and no questions back.

## Grading

| Grade | Condition | Next |
|---|---|---|
| PASS | At least 4 of 5 inferences cover every key beat of the intent, including the bidirectional, edge or scope beat. Different wording is fine. | Idempotency rounds |
| PARTIAL | The inferences consistently catch one side of a two-sided rule, or stretch into a neighbouring concern. | Revise, run again |
| FAIL | Inferences diverge, or miss the core beat. | Revise, run again |

## Idempotency

After a first PASS, run two more rounds with five fresh agents each: 15 inferences in total. All three rounds must pass with no new systematic miss. A later round that regresses counts as PARTIAL.

## Stopping

- Three of three rounds pass: apply the label.
- Three revisions without a PASS: stop, and hand back the best candidate together with the miss that kept recurring.

## Defaults

| Stakes | Agents | Rounds |
|---|---|---|
| normal | 5 | 3 |
| high (top-level skill names, protocol names) | 7 | 3 |
| throwaway header | 3 | 2 |

Word cap 80; at most 3 revision iterations.

## Anti-patterns

- Showing the agents the body. That tests the body, not the label.
- Running agents one after another; later ones anchor on earlier answers.
- Changing one word after a FAIL. A FAIL means the concept behind the label is off; rethink it.
- Accepting "mostly right". For a one-sided result, either fix the label or split the rule so each part has a label that fits.