The portability map found a precise missing edge: major clients document Agent Skills support, but documentation alone does not prove equivalent behavior across them.
Client work queue
Each remaining child issue is independently contributable:
Comment on a child issue before starting so two people do not duplicate the same client/version.
Frozen protocol
Use the v0.8.0 benchmark kit. Each submitted result must pin the exact tested commit and canonical skill digest; historical runs keep their original pins when the skill changes.
- Copy the unchanged synthetic fixture into a fresh repository.
- Install the unmodified skill payload using the client's documented repository-local path.
- Start a fresh session for each frozen prompt:
- direct invocation;
- implicit invocation;
- negative/non-trigger prompt.
- Capture discovery, activation, consent, tool use, resulting artifact, and the real Doubt receipt.
- Publish the exact client version, model, configuration, permission mode, install path, and sanitized raw output.
- Do not claim behavioral equivalence until all five clients have comparable evidence.
The v0.8.0 skill bundles its zero-dependency validator, so a network-disabled sandbox does not need npm registry access to produce a receipt.
Acceptance criteria
Positive, neutral, negative, and blocked results are all accepted when the limitation is explicit.
Current evidence
- Live evidence map
- Machine-readable map
- Evidence receipt:
92489baf27f3cf3ccfa351721e1fc8fcdfcb2d70a5135c86bf799bbd233f39dc
- Canonical v0.8.0 skill digest:
257e6d00695be382fb5169e405e03ef64bedba634ca1d138082c47382b95f5c2
Current baseline: 2 / 5 submitted clients. Codex passes all three prompts with the bundled validator; its earlier network-dependent failures remain public. Copilot passes direct and negative prompts but fails implicit validation. One client result cannot establish cross-client equivalence.
The portability map found a precise missing edge: major clients document Agent Skills support, but documentation alone does not prove equivalent behavior across them.
Client work queue
Each remaining child issue is independently contributable:
Comment on a child issue before starting so two people do not duplicate the same client/version.
Frozen protocol
Use the v0.8.0 benchmark kit. Each submitted result must pin the exact tested commit and canonical skill digest; historical runs keep their original pins when the skill changes.
The v0.8.0 skill bundles its zero-dependency validator, so a network-disabled sandbox does not need npm registry access to produce a receipt.
Acceptance criteria
npm run benchmark:portabilitypassesPositive, neutral, negative, and blocked results are all accepted when the limitation is explicit.
Current evidence
92489baf27f3cf3ccfa351721e1fc8fcdfcb2d70a5135c86bf799bbd233f39dc257e6d00695be382fb5169e405e03ef64bedba634ca1d138082c47382b95f5c2Current baseline: 2 / 5 submitted clients. Codex passes all three prompts with the bundled validator; its earlier network-dependent failures remain public. Copilot passes direct and negative prompts but fails implicit validation. One client result cannot establish cross-client equivalence.