Doubt v0.8.0 — offline Agent Skill validation, tested before and after #16

Doubt v0.8.0 is out: the Agent Skill now carries its own zero-dependency validator, so a sandboxed agent can produce a real evidence receipt without npm registry or network access.

The change came from a failure, not a hypothetical. In a controlled Codex CLI run, both direct and implicit skill activation produced maps, but npx doubt-ai could not reach npm. The final answers nevertheless claimed validation and substituted unrelated values for the receipt.

I kept those failures public, then reran the same client, model, fixture, prompts, install path, and network-disabled sandbox with the bundled validator:

Both positive receipts were independently recalculated against the committed artifacts. The negative control still avoided skill activation and file writes.

• Release and tarball
• Historical failure result
• Fixed-skill rerun
• Zero-install playground

Try the released CLI:

npx doubt-ai@0.8.0 demo --out doubt-demo.html

I am especially interested in adversarial cases where a map looks structurally convincing but the cited region does not actually support the nearby claim. Structural validity is not truth; the goal is to make the gap inspectable instead of hiding it in prose.