adversarial-critique

adversarial-critique is a skill for Claude Code, Codex from Ridwannurudeen/hermes-council. It costs 32 tokens per session (1,117 once invoked), scanned A, original, MIT.

A method for combining evidence while updating how likely a belief is. Bayesian reasoning starts with an initial estimate, adjusts it as evidence arrives, and records what remains uncertain.

In plain words
What is it for?
Use it to compare uncertain options, make forecasts, combine studies, and identify what evidence could change a conclusion.
Why use it?
It helps keep confidence aligned with the available evidence when the answer is unclear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare uncertain options, make forecasts, combine studies, and identify what evidence could change a conclusion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ridwannurudeen/hermes-council/adversarial-critique
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 Ridwannurudeen/hermes-council --skill adversarial-critique
Clone the repo
git clone --depth 1 https://github.com/Ridwannurudeen/hermes-council

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 adversarial-critique

README.md
[![agentmods](https://agentmods.dev/badge/skills/ridwannurudeen/hermes-council/adversarial-critique/github.svg)](https://agentmods.dev/skills/ridwannurudeen/hermes-council/adversarial-critique)
Your own site
<a href="https://agentmods.dev/skills/ridwannurudeen/hermes-council/adversarial-critique"><img src="https://agentmods.dev/badge/skills/ridwannurudeen/hermes-council/adversarial-critique/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 adversarial-critique

Your own site · 80×15
<a href="https://agentmods.dev/skills/ridwannurudeen/hermes-council/adversarial-critique"><img src="https://agentmods.dev/badge/skills/ridwannurudeen/hermes-council/adversarial-critique.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,117 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.
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 $0.00032 $0.01117
Opus 5 $0.00016 $0.00558
Sonnet 5 $0.00006 $0.00223
Haiku 4.5 $0.00003 $0.00112

Measured 12d ago against content hash 4254bd5c81ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

adversarial-critique 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 12d 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/council/adversarial-critique/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Critique

Use council_evaluate, council_review_plan, council_review_diff, and council_preflight to stress-test work before it goes live. The council's adversarial structure surfaces blind spots that self-review misses.

When to Use

  • Before publishing: Evaluate research, articles, or analysis
  • Before deploying: Gate code deployments with safety review
  • Before sending: Review messages or communications for tone and accuracy
  • During development: Get structured feedback on design decisions
  • After completion: Retrospective quality check on finished work

Tools

council_evaluate -- Quality Assessment

council_evaluate(
    content="[your work product]",
    question="[what task it was supposed to accomplish]",
    criteria=["accuracy", "depth", "falsifiability", "evidence"]
)

Returns per-persona feedback and an overall confidence score.

council_gate -- Safety Check

council_gate(
    action="Deploy v2.0 to production with new authentication system",
    risk_level="high",
    context="New auth uses JWT tokens instead of session cookies. All tests pass."
)

Returns verdict (allow, allow_with_conditions, or deny), blocking risks, required checks, safe alternatives, and reasoning. Uses abbreviated council (Skeptic + Oracle + Arbiter) for speed.

Risk level thresholds:

  • low: Allowed if confidence >= 30%
  • medium: Allowed if confidence >= 50%
  • high: Allowed if confidence >= 70%

council_review_plan -- Plan Review

council_review_plan(
    plan="[implementation plan]",
    objective="Ship the feature without breaking existing integrations",
    risk_level="medium"
)

council_review_diff -- Diff Review

council_review_diff(
    diff="[git diff]",
    objective="Review for bugs, security regressions, and missing tests",
    files=["src/auth.py", "tests/test_auth.py"]
)

council_preflight -- Action Gate

council_preflight(
    action="Run production migration",
    risk_level="high",
    context="Migration backfills NULL emails before adding NOT NULL",
    checks=["backup exists", "rollback SQL written"]
)

Read the full file on GitHub · 150 lines

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. 12d ago First seen · 150 lines · 32 tokens per session scan A 4254bd5c81ec

Subscribe to this mod's changes

adversarial-critique is a skill published in the GitHub repository Ridwannurudeen/hermes-council (50 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,117 once invoked, about $0.0002 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.