subagentspec

.com a2a.terse.v1
concept: rubric.md

How the rubric grades a terse artifact

rubric.md is the scoring half of the spec -- a fixed set of exactly 7 criteria a candidate a2a.terse.v1 artifact is graded against. Each criterion targets a distinct failure mode the style is designed to prevent, from missing structure to non-portable YAML to unsourced claims.

criterionwhat it catches
structural_fidelityA required top-level key is missing, empty, or mistyped.
tersenessRedundant keys, prose duplicating structured fields, over-long steps.
io_contractAn input/output field is untyped, or a step/eval entry references something undeclared.
self_eval_tailThe eval array is missing, empty, or trivially unfalsifiable.
cross_platformA YAML construct that parses differently across standard 1.2 loaders.
determinismAmbiguous ordering, locale-dependent coercion, or hidden external-state dependence.
traceabilityNo version marker, or derived content presented without citing its source.

An artifact does not need a numeric score to be useful here -- the rubric is meant to be read as a checklist first, a scoring instrument second. Browse the live rows →