# Spec Provenance Review

Flag concrete false-positive proof introduced by changed specs, not test helper or...

- Repository: https://github.com/different-ai/openwork (24362 stars)
- Category: Testing
- License: see repository
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add different-ai/openwork --skill spec-provenance-review -g -a claude-code -y`
Codex: `npx skills add different-ai/openwork --skill spec-provenance-review -g -a codex -y`
Cursor: `npx skills add different-ai/openwork --skill spec-provenance-review -g -a cursor -y`
Gemini CLI: `npx skills add different-ai/openwork --skill spec-provenance-review -g -a gemini-cli -y`

## Description

Flag concrete false-positive proof introduced by changed specs, not test helper or channel preferences. Advisory only; never gates Warden clearance.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

Review changes under `evals/specs/**` and `evals/worlds/**` for one question:
does this diff let a spec pass while the specific behavior it claims to test
is broken?

Test code has a different purpose from production code. Review the validity
of its evidence, not production hardening, abstraction, style, or preferred
helper usage. Channel conventions in `evals/README.md` are authoring guidance;
a channel mismatch alone is not a finding.

Report a MEDIUM (advisory) finding only when ALL of these hold:

- The changed lines introduce or materially worsen the gap.
- The spec bypasses the behavior under test or asserts evidence unrelated to
  that behavior.
- You can identify a concrete broken behavior that would still pass, grounded
  in the spec and relevant implementation. A hypothetical possibility or the
  availability of a different helper is insufficient.

Examples worth reporting:

- A spec claims a person can submit a form, but directly invokes the API and
  never submits through the UI, so broken form wiring is not exercised.
- A spec claims a save persists data, but only asserts the seeded value and
  never observes the result of saving.
- A spec claims visible success, but checks an internal success flag while
  the implementation demonstrably never renders the result.

Do not report:

The rest: https://github.com/different-ai/openwork/blob/HEAD/.warden/skills/spec-provenance-review/SKILL.md