| name | tbm-adversarial-defender |
| description | Thin Codex wrapper for TBM adversarial defender mode. Use when LT wants this Codex session to defend a plan or artifact live while pasting attacks from another model. Delegates to the canonical repo skill at `C:\Dev\tbm-apps-script\.claude\skills\adversarial-defender\SKILL.md`. |
TBM Adversarial Defender
This is a Codex adapter, not a second source of truth.
The canonical workflow lives in C:\Dev\tbm-apps-script\.claude\skills\adversarial-defender\SKILL.md.
Before acting
- Read
C:\Dev\tbm-apps-script\.claude\skills\adversarial-defender\SKILL.md.
- Confirm the defended artifact, rival model, evidence bar, environment access, and exit condition.
Validation
Before relying on this wrapper, verify this file exists:
C:\Dev\tbm-apps-script\.claude\skills\adversarial-defender\SKILL.md
If it is missing, treat the wrapper as stale and say so explicitly instead of guessing.
Adapter rules
- Keep the repo skill canonical for the output contract and forbidden moves.
- Use this wrapper when the user wants live defender behavior in-thread, not prompt generation.
- If the user wants external prompts for both sides instead of live defender behavior, prefer
tbm-adversarial-review.