adversarial-stress-testing

adversarial-stress-testing is a skill for Claude Code, Codex from yogsoth-ai/stress-test. It costs 69 tokens per session (1,253 once invoked), scanned A, a copy of adversarial-stress-testing, Apache-2.0.

A method for testing whether claims, ideas, experiments, or other artifacts fail at logical limits and unusual boundary cases. It uses counterexamples and extreme conditions to map where an artifact remains valid.

In plain words
What is it for?
Use it to challenge claims, research questions, approaches, and experiment designs. It can test assumptions, enumerate boundary cases, choose critical tests, and map the conditions under which conclusions hold.
Why use it?
Normal examples may not reveal hidden assumptions or failure points. Deliberately seeking cases where the reasoning breaks makes its limits clearer.

Skill for Claude CodeCodex

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

Good fit Use it to challenge claims, research questions, approaches, and experiment designs. It can test assumptions, enumerate boundary cases, choose critical tests, and map the conditions under which conclusions hold.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogsoth-ai/stress-test/adversarial-stress-testing
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 yogsoth-ai/stress-test --skill adversarial-stress-testing
Clone the repo
git clone --depth 1 https://github.com/yogsoth-ai/stress-test

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-stress-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/adversarial-stress-testing/github.svg)](https://agentmods.dev/skills/yogsoth-ai/stress-test/adversarial-stress-testing)
Your own site
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/adversarial-stress-testing"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/adversarial-stress-testing/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-stress-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/adversarial-stress-testing"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/adversarial-stress-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,253 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 91% copy Near-identical to another mod 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 $0.00069 $0.01253
Opus 5 $0.00034 $0.00626
Sonnet 5 $0.00014 $0.00251
Haiku 4.5 $0.00007 $0.00125

Measured 8d ago against content hash 03947096304a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adversarial-stress-testing 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 8d 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.

Origin

This is a copy

91% identical to adversarial-stress-testing — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/adversarial-stress-testing/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Stress Testing

Core Question: Does this artifact collapse under logical limits and boundary conditions?

Methodology Sources

  • Lakatos (1976) — Proofs and Refutations: counterexample-driven refinement
  • Dutilh Novaes (2016) — Adversarial argumentation as dialogical practice
  • Clarke BVA — Boundary Value Analysis for systematic edge testing
  • Flyvbjerg (2006) — Critical case methodology: most-likely/least-likely selection
  • Popper (1959) — Falsificationism: seek conditions where claims break

Strategy Routing

Artifact Type Primary Strategy Rationale
claim, hypothesis assumption-negation Direct logical attack
gap, research-question lakatos-heuristics Counterexample refinement
idea, approach boundary-enumeration Parameter space testing
experiment-design critical-case-design Decisive test selection
any (synthesis) validity-envelope-mapping Comprehensive envelope

Budget Table

Resource S M L
Negation derivation chains 3 6 10
Counterexamples/boundary cases 5 12 25
Parameter dimensions 3 6 10
Validity envelope dimensions 2 4 6

Tactics

  • contradiction-derivation — Negate, derive, detect contradiction
  • boundary-probing — Map parameter space, test extremes, find breakpoints
  • counterexample-heuristics — Generate monsters, bar or incorporate

Context Management

  • Persist derivation chains and counterexamples across rounds
  • Track which negations produced genuine contradictions vs. benign outcomes
  • Accumulate validity envelope boundaries incrementally

Output

Produces AdversarialStressReport containing: identified breakpoints, validity envelope, surviving refined claims, and confidence assessment.

Available Strategies

Optional, no fixed order; the final leaf is always a sop.

Strategy When to use
assumption-negation Classic reductio ad absurdum: negate the core claim, derive logical consequences, seek contradiction or absurdity.
boundary-enumeration Systematic Boundary Value Analysis: identify parameter boundaries, test at and beyond limits, detect breakpoints.
critical-case-design Flyvbjerg critical case methodology: select most-likely and least-likely cases to maximize inferential power.
lakatos-heuristics Proofs and Refutations method: generate counterexamples, attempt monster-barring, incorporate surviving counterexamples as lemma refinements.
stress-test-validity-envelope-mapping Map the complete validity envelope of a claim across all relevant dimensions, synthesizing breakpoints into a bounded region.

Read the full file on GitHub · 122 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. 8d ago First seen · 122 lines · 69 tokens per session scan A 03947096304a

Subscribe to this mod's changes

adversarial-stress-testing is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,253 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to adversarial-stress-testing, differing in 2 lines, and is treated as a copy.