Omh Adversarial Consensus
[omh] Technical proposal facing adversarial scrutiny: independent perspectives attack a...
Install
npx skills add rlaope/oh-my-hermes --skill omh-adversarial-consensus -g -a claude-code -y- Repository
- rlaope/oh-my-hermes5k
- Category
- Engineering
- Updated
- 3d ago
- License
- MIT
- Context cost
- Mediumabout 2,628 tokens
- Runs scripts
- No, instructions only
What it does
[omh] Technical proposal facing adversarial scrutiny: independent perspectives attack a proposal, then distill into a bundle a separate planner consumes. Use when the user says: adversarial-consensus, adversarial planning, adversarial plan review, red team this plan, red-team this plan, red team the proposal, multi-perspective review, multiple perspectives.
Adversarial Consensus
This is an OMH adversarial-consensus workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Why This Exists
adversarial-consensus exists because agreement reached by perspectives that read each other is not review, it is convergence. Independent findings, an attack round nobody is allowed to defend against, and a distillation that may only subtract produce objections a single planning pass never surfaces, and the mandatory handoff keeps that bundle from being mistaken for the plan.
Do Not Use When
- The user wants the plan itself, with options, acceptance criteria, and verification commands; use
ulw-plan, which this workflow feeds. - The request is still too ambiguous to state the proposal being attacked; use
ulw-interviewfirst. - The user wants completed code reviewed for defects rather than a proposal attacked before it is built; use
omh-code-review. - The user wants hostile runtime scenarios against a built change; use
ulw-qa. - One perspective would do: a small local change with no contested decision does not earn three rounds.
Examples
Good example:
- Prompt: $adversarial-consensus we plan to move session state into Redis before the launch, attack it from every angle before I write the plan.
- Expected behavior: Name the roster and their distinct angles, take blind findings from each, run one attack-only round, resolve each objection to defend/refine/concede, distill only into the four buckets, and hand the bundle to
ralplanas planning input. - Why: The decision is contested and pre-plan, which is exactly where independent objections are worth more than one planner's confidence.
Bad example:
