omh-adversarial-consensus

omh-adversarial-consensus is a skill for Claude Code, Codex from rlaope/oh-my-hermes. It costs 77 tokens per session (2,234 once invoked), scanned A, original, MIT.

A workflow for having independent perspectives examine a proposal, attack it in a separate challenge round, and distill the objections before planning.

In plain words
What is it for?
It helps test contested technical proposals before they are built, when the proposal is clear enough to challenge.
Why use it?
It surfaces objections that one planning pass may miss and keeps the resulting review separate from the plan itself.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; $skill-name invocation.

Good fit It helps test contested technical proposals before they are built, when the proposal is clear enough to challenge.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rlaope/oh-my-hermes/omh-adversarial-consensus
About the project

oh-my-hermes is an operating layer for Hermes Agent that organizes requests into workflows for planning, research, creation, coding handoffs, operations, and project memory. Hermes users run these workflows through the desktop app, CLI, or messenger app, while the catalogue add-ons extend its native capabilities.

rlaope/oh-my-hermes · 1,677 stars · on GitHub · rlaope.github.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add rlaope/oh-my-hermes --skill omh-adversarial-consensus
Clone the repo
git clone --depth 1 https://github.com/rlaope/oh-my-hermes

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for omh-adversarial-consensus

README.md
[![agentmods](https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-adversarial-consensus/github.svg)](https://agentmods.dev/skills/rlaope/oh-my-hermes/omh-adversarial-consensus)
Your own site
<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/omh-adversarial-consensus"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-adversarial-consensus/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omh-adversarial-consensus

Your own site · 80×15
<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/omh-adversarial-consensus"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-adversarial-consensus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,234 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.02234
Opus 5 $0.00039 $0.01117
Sonnet 5 $0.00015 $0.00447
Haiku 4.5 $0.00008 $0.00223

Measured 3d ago against content hash d4d70f40b576, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

omh-adversarial-consensus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/omh-adversarial-consensus/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Consensus

This is a Hermes-native adversarial-consensus workflow skill.

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 ralplan, which this workflow feeds.
  • The request is still too ambiguous to state the proposal being attacked; use deep-interview first.
  • The user wants completed code reviewed for defects rather than a proposal attacked before it is built; use code-review.
  • The user wants hostile runtime scenarios against a built change; use ultraqa.
  • 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 ralplan as 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:

  • Prompt: $adversarial-consensus give me the migration plan with the steps and the rollout order.
  • Expected behavior: Produce the distilled bundle and hand it to ralplan; the steps and rollout order are the planner's output, not this workflow's.
  • Why: The bundle is INPUT to planning. Emitting a plan here skips the reviewed-plan gate and turns the buckets into a task list.

Read the full file on GitHub · 138 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed d4d70f40b576
  2. 8d ago Changed 1afbc6d64535
  3. 12d ago First seen · 138 lines · 77 tokens per session scan A 3a216cc1fa8f

Subscribe to this mod's changes

omh-adversarial-consensus is a skill published in the GitHub repository rlaope/oh-my-hermes (1,677 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 2,234 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

story-review

A review process for finding problems in a novel’s structure, characters, wording, and world rules. It can use several reviewers or one reviewer when others are unavailable.

uu201/character-arc · 74 tokens

story-long-analyze

A structured process for deeply analysing a long online novel, starting with its opening three chapters and continuing chapter by chapter.

uu201/character-arc · 175 tokens

moxiangtongxiu-perspective

A Chinese-language creative-writing guide built around character-led stories, interwoven plotlines, memorable dialogue, ensemble casts, and emotional contrasts. It is presented as a perspective associated with the author Mo Xiang Tong Xiu.

momozi1996/awesome-ai-persona-skills · 136 tokens

tiancantudou-perspective

A creative-writing guide based on the storytelling patterns associated with Chinese web novelist Tiancan Tudou. It focuses on stories where an underestimated character grows stronger through challenges and moves into new settings.

momozi1996/awesome-ai-persona-skills · 158 tokens

tianya-gods-team

A decision-making system in which 20 fictional specialist viewpoints analyze one question in parallel before a coordinating AI combines them. It covers areas such as history, economics, relationships, technology, mysteries, and culture.

momozi1996/awesome-ai-persona-skills · 230 tokens

browser-cdp

Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…

uu201/character-arc · 94 tokens