counterexample-heuristics

counterexample-heuristics is a skill for Claude Code, Codex from yogsoth-ai/stress-test. It costs 31 tokens per session (426 once invoked), scanned A, original, Apache-2.0.

A method for testing a claim by deliberately looking for counterexamples, meaning cases where the claim fails. It can exclude invalid cases or revise the claim so it states a narrower, defensible rule.

In plain words
What is it for?
Use it to challenge theorems, hypotheses, or general rules with edge cases, then refine or reject them based on what survives.
Why use it?
It finds boundary cases and unusual situations that broad claims often miss. Surviving counterexamples can improve the claim instead of being ignored.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to challenge theorems, hypotheses, or general rules with edge cases, then refine or reject them based on what survives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogsoth-ai/stress-test/counterexample-heuristics
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 counterexample-heuristics
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 counterexample-heuristics

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/counterexample-heuristics"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/counterexample-heuristics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 426 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 $0.00031 $0.00426
Opus 5 $0.00015 $0.00213
Sonnet 5 $0.00006 $0.00085
Haiku 4.5 $0.00003 $0.00043

Measured 9d ago against content hash b716bc068c21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

counterexample-heuristics 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 9d 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/counterexample-heuristics/SKILL.md · 58 lines

What it actually says

Counterexample Heuristics

Orchestration Steps

  1. Receive claim/theorem from strategy
  2. Dispatch counterexample-generation to produce candidate monsters
  3. For each counterexample: a. Dispatch monster-barring-attempt — can it be excluded legitimately? b. If barring succeeds: record as excluded, note narrowed scope c. If barring fails: counterexample is genuine
  4. For genuine counterexamples, dispatch claim-refinement:
    • Incorporate as lemma (add condition to claim)
    • Or weaken claim scope
  5. Report: original claim, counterexamples found, refined claim

Subagents

  • counterexample-generation
  • monster-barring-attempt
  • claim-refinement

Termination Conditions

  • All generated counterexamples resolved (barred or incorporated)
  • Claim refined to survive all counterexamples (success)
  • Claim collapses entirely under counterexamples (falsified)
  • Budget exhausted (report current state)

Available SOPs

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

SOP When to use
claim-refinement Propose a refined claim that survives counterexamples while preserving maximum explanatory power (Lakatos lemma-incorporation).
counterexample-generation Systematically generate counterexamples (monsters) to a given claim using diverse heuristic strategies.
monster-barring-attempt Attempt to exclude a counterexample as illegitimate by tightening definitions or preconditions (Lakatos monster-barring).
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. 9d ago First seen · 58 lines · 31 tokens per session scan A b716bc068c21

Subscribe to this mod's changes

counterexample-heuristics is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 426 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 2026-08-31.

Related

Other skills, from other repositories

relax-dev-debug

Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.

redai-infra/Relax · 60 tokens

research-ideation

Quant-focused research ideation pipeline: scope selection (3 stages) → anchor-first literature grounding → single-core idea generation → iterative refinement → ELO tournament ranking (Final = N+R+C−D) → update evo-memory → user selects direction → expand into manuscript-quality proposal. Optimized for incremental…

CamusGIT/EvoQuant · 151 tokens

quant-experiment-runtime

Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…

CamusGIT/EvoQuant · 179 tokens

local-paper-navigator

Find and read papers from the local papers library (repo papers/, mounted at /papers/). Three native tools form a reading funnel: papersearch (one line per paper), paperread (card + section outline), papersection (one verbatim section — the only full-text access). Use when: find papers in the local library, read a…

CamusGIT/EvoQuant · 119 tokens

experiment-pipeline

Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and…

CamusGIT/EvoQuant · 129 tokens

paper-review

Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writing clarity, results quality, testing completeness, method design), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust…

CamusGIT/EvoQuant · 152 tokens