minimal-change-search

minimal-change-search is a skill for Claude Code, Codex from yogsoth-ai/stress-test. It costs 29 tokens per session (588 once invoked), scanned A, original, Apache-2.0.

A search for the smallest change that would reverse a conclusion. It tests different factors with gradually larger changes and reports the nearest point where the conclusion flips.

In plain words
What is it for?
Use it to test causal claims, build counterfactual scenarios, and measure sensitivity to changing conditions.
Why use it?
It reveals how fragile a conclusion is and which factor is most likely to change it.

Skill for Claude CodeCodex

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

Good fit Use it to test causal claims, build counterfactual scenarios, and measure sensitivity to changing conditions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogsoth-ai/stress-test/minimal-change-search
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 minimal-change-search
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 minimal-change-search

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/minimal-change-search"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/minimal-change-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 588 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 $0.00029 $0.00588
Opus 5 $0.00015 $0.00294
Sonnet 5 $0.00006 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured 7d ago against content hash 5a357ebdcea7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

minimal-change-search 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 7d 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/minimal-change-search/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Minimal Change Search Tactic

Find the smallest perturbation that flips the conclusion — closer flip-points mean higher fragility.

Orchestration

  1. causal-claim-extraction identifies the conclusion to test
  2. factor-enumeration generates candidate change dimensions
  3. counterfactual-scenario-construction builds scenarios with graduated changes
  4. flip-point-detection binary-searches for the minimal change that flips
  5. fragility-measurement computes distance from actuality to flip-point
  6. Repeat for each dimension within budget
  7. Report: nearest flip-point, fragility index, most vulnerable dimension

Search Strategy

  • Start with large changes (clearly flips or clearly holds)
  • Binary search between hold/flip boundary
  • Record the minimal change magnitude per dimension
  • Fragility = 1 / (distance to nearest flip-point)

Subagents Dispatched

  • causal-claim-extraction (conclusion identification)
  • factor-enumeration (dimension generation)
  • counterfactual-scenario-construction (graduated scenarios)
  • flip-point-detection (binary search)
  • fragility-measurement (distance computation)

Termination Conditions

  • All dimensions searched within budget
  • Flip-point found with distance < threshold (extremely fragile)
  • No flip-point found after maximum search depth (robust)

Available SOPs

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

SOP When to use
causal-claim-extraction Extract all causal claims (X causes Y, X leads to Y, X enables Y) from an artifact, producing a structured list of cause-effect pairs.
counterfactual-scenario-construction Construct precise, internally consistent counterfactual scenarios where specified factors are altered, then reason about the resulting conclusion.
factor-enumeration List all key factors, conditions, and assumptions that support or enable the artifact's conclusion.
flip-point-detection Find the minimal change magnitude along a dimension that causes the conclusion to flip from true to false.
fragility-measurement Compute a fragility index from flip-point distances and degradation scores, summarizing how robust the conclusion is.

Read the full file on GitHub · 69 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. 7d ago First seen · 69 lines · 29 tokens per session scan A 5a357ebdcea7

Subscribe to this mod's changes

minimal-change-search is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 588 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

tournament-judge

Runs a domain-neutral, evidence-based tournament in which independent candidates are reviewed, anonymized, and scored by a blind judge against a rubric fixed before judging. Use when comparing competing plans, designs, implementations, documents, tools, vendors, strategies, or other substantial options; when the user…

alextverdyy/tournament-judge · 105 tokens

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

browser_cdp

A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.

mateaix/mateclaw · 44 tokens

shogun-screenshot

A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.

yohey-w/multi-agent-shogun · 149 tokens

creating-skills

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…

redai-infra/Relax · 70 tokens