@amethystluna/logicprobe

Usage

The plugin auto-injects a capability notification into the first model step. The skill activates when its Use when description matches your task:

• Design doc / plan review — "Review this design document" → claim enumeration and codebase verification
• Behavioral questions — "could this state machine deadlock", "is this retry limit safe", "check this timing for bugs" → the skill is proactively suggested (not auto-loaded) as an optional verification pass
• Refactoring plans — the pipeline compares before/after models to flag undocumented behavioral changes

The skill auto-classifies depth (LIGHTWEIGHT / STANDARD / ESCALATED) from plan features in Phase 0, and appends a ## Plan Verification summary block as the audit trail.

Python is optional: when available, the reusable harness at references/verification-harness.py runs the checks; when not (air-gapped machines), the guide at references/logic-verification-guide.md provides a manual verification mode.

Configuration

In DeepSeek Harness, the bundle accepts a small configuration object:

Key	Type	Default	Description
enabled	boolean	true	Set to false to disable the session-start gate injection.
gateContent	string	built-in gate text	Override the text injected into the first model step.

To change it, override the row by id in your profile's cordis.patch.yml:

- insert:
    - id: logicprobe
      name: '@amethystluna/logicprobe'
      config:
        enabled: true
        gateContent: |
          ...