factor-removal

factor-removal is a skill for Claude Code, Codex from yogsoth-ai/stress-test. It costs 32 tokens per session (764 once invoked), scanned A, original, Apache-2.0.

An ablation-style test that removes supporting factors one at a time to see whether a conclusion still holds. An ablation study checks what changes when one part of a system or explanation is taken away.

In plain words
What is it for?
Use it to test the stability of a conclusion, compare altered scenarios, measure how much it weakens, and rank the factors carrying the most weight.
Why use it?
It shows which assumptions or conditions are essential and which have little effect on the result.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/yogsoth-ai/stress-test/factor-removal
Any agent
npx skills add yogsoth-ai/stress-test --skill factor-removal
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 factor-removal

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/factor-removal.svg)](https://agentmods.dev/skills/yogsoth-ai/stress-test/factor-removal)
Your own site
<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/factor-removal"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/factor-removal.svg" alt="Measured on agentmods" 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 764 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00764
Opus 5 $0.00016 $0.00382
Sonnet 5 $0.00006 $0.00153
Haiku 4.5 $0.00003 $0.00076

Measured 5d ago against content hash 5989ee2eef15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

factor-removal 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 5d 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/factor-removal/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Factor Removal Strategy

Ablation study approach: systematically remove each factor and observe conclusion stability.

Method

  1. factor-enumeration lists all factors supporting the conclusion
  2. single-factor-removal removes one factor at a time
  3. counterfactual-scenario-construction reasons about the modified scenario
  4. fragility-measurement scores how much the conclusion degrades
  5. load-bearing-identification ranks factors by impact of removal
  6. Optional: flip-point-detection for partial removal (dose-response)

Budget Table

Parameter S M L
Factors removed 5 10 20
Removal iterations 1 2 3
Combination removals 0 3 8

Orchestration

factor-enumeration → [rank by suspected importance]
→ [for each factor]:
    single-factor-removal
    → counterfactual-scenario-construction
    → fragility-measurement
→ [if budget allows, test combinations]:
    single-factor-removal (multiple factors)
    → counterfactual-scenario-construction
→ load-bearing-identification (final ranking)

Subagents

  • factor-enumeration (factor listing)
  • single-factor-removal (ablation)
  • counterfactual-scenario-construction (scenario reasoning)
  • fragility-measurement (degradation scoring)
  • load-bearing-identification (ranking)
  • flip-point-detection (dose-response, optional)

Available Tactics

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

Tactic When to use
minimal-change-search Tactic: Generate candidate changes, detect flip-points where conclusion reverses, measure fragility as distance to nearest flip.
systematic-factor-ablation Tactic: List all factors, remove one at a time, assess conclusion stability, rank factors by load-bearing importance.

Available SOPs

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

SOP When to use
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.
load-bearing-identification Identify which factors are "load-bearing walls" — factors whose removal would collapse the conclusion.
single-factor-removal Remove one specified factor from the artifact's support structure and reason about how the conclusion changes.

Read the full file on GitHub · 91 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. 5d ago First seen · 91 lines · 32 tokens per session scan A 5989ee2eef15

Subscribe to this mod's changes

factor-removal is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 764 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

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

labrat-operator

Use when operating a labrat lab with Codex: checking health, choosing the next phase prompt, supervising runtime cycles, auditing candidates, synthesizing recent evaluations, or writing checkpoint notes.

ProjectDXAI/labrat · 42 tokens