apply-adversarial-verification

apply-adversarial-verification is a skill for Claude Code from jeffreytse/grimoire-core. It costs 51 tokens per session (2,308 once invoked), scanned A, original, MIT.

A method for checking claims from someone who may benefit from misleading you, using tests, inconsistency checks, and independent confirmation.

In plain words
What is it for?
Use it to verify supplier claims, competitor information, reports, security findings, or other evidence gathered in adversarial situations.
Why use it?
It prevents decisions from relying on unverified statements in situations where the information source has conflicting interests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grimoire-business plugin — 156 skills shipped together

Good fit Use it to verify supplier claims, competitor information, reports, security findings, or other evidence gathered in adversarial situations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/apply-adversarial-verification
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 jeffreytse/grimoire-core --skill apply-adversarial-verification
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 156 skills.

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 apply-adversarial-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-adversarial-verification/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-adversarial-verification)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-adversarial-verification"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-adversarial-verification/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 apply-adversarial-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-adversarial-verification"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-adversarial-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,308 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 $0.00051 $0.02308
Opus 5.5 $0.00020 $0.00923
Sonnet 5.5 $0.00010 $0.00462
Haiku 4.5 $0.00005 $0.00231

Measured 1mo ago against content hash 50a5089ce6de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

apply-adversarial-verification 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 1mo 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/business/strategy/skills/apply-adversarial-verification/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply Adversarial Verification

When information comes from a party with motivation to mislead, verify using designed tests, inconsistency detection, and independent corroboration — because in adversarial conditions, accepting stated information at face value is not due diligence, it is assumption.

Why This Is Best Practice

Why best: The 察智部 (Investigative Wisdom) of 智囊 contains dozens of historical anecdotes organized around a common pattern: an official, general, or judge receives information and must determine whether it is genuine or falsified. The recurring methodology across these cases: (1) design a test whose outcome depends on the truth — if the claim is true, X will happen; if false, Y; (2) look for inconsistencies between what was stated and what the physical evidence shows; (3) obtain corroboration from sources who have not been able to coordinate their story. This methodology is explicit in the text: "察" (察智) means investigative perception — seeing through the surface to the actual state.

CIA "Psychology of Intelligence Analysis" (Richards Heuer, 1999): Heuer's foundational work on intelligence analysis methodology establishes that the human mind naturally seeks confirming evidence and is systematically poor at detecting deception. His proposed counter: Analysis of Competing Hypotheses (ACH) — for each competing explanation, identify what evidence each hypothesis PREDICTS and test against observed evidence. Hypotheses that make false predictions are eliminated. Standard methodology at CIA, DIA, and major intelligence services globally; taught in intelligence analysis programs at George Washington University, King's College London, and others.

M&A due diligence practice: Every significant acquisition involves adversarial verification because the seller has motivation to present the company favorably and conceal liabilities. Standard due diligence methodology: verify stated financials against third-party records (bank statements, tax filings); look for inconsistencies between management representations and operational data; interview customers and employees independently (without allowing management to filter access). The $30B+ due diligence industry exists precisely because self-reported information in adversarial contexts is unreliable. Required by fiduciary duty at every major investment bank and private equity firm.

Read the full file on GitHub · 73 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. 1mo ago First seen · 73 lines · 51 tokens per session scan A 50a5089ce6de

Subscribe to this mod's changes

apply-adversarial-verification is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 2,308 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.