inversion

inversion is a skill for Claude Code, Codex from guia-matthieu/clawfu-skills. It costs 96 tokens per session (3,668 once invoked), scanned A, original, MIT.

A problem-solving method that starts by asking what would cause failure, then works backward to avoid those causes. It applies the idea of inversion associated with mathematician Carl Jacobi and investor Charlie Munger.

In plain words
What is it for?
Use it for goal setting, risk analysis, decision making, problem solving, strategy, and personal development.
Why use it?
It helps reveal risks and overlooked assumptions that a direct plan may miss. Looking at worst outcomes can make decisions and goals more realistic.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it for goal setting, risk analysis, decision making, problem solving, strategy, and personal development.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guia-matthieu/clawfu-skills/inversion
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 guia-matthieu/clawfu-skills --skill inversion
Clone the repo
git clone --depth 1 https://github.com/guia-matthieu/clawfu-skills

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 inversion

README.md
[![agentmods](https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/inversion/github.svg)](https://agentmods.dev/skills/guia-matthieu/clawfu-skills/inversion)
Your own site
<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/inversion"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/inversion/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 inversion

Your own site · 80×15
<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/inversion"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/inversion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,668 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 $0.00096 $0.03668
Opus 5 $0.00048 $0.01834
Sonnet 5 $0.00019 $0.00734
Haiku 4.5 $0.00010 $0.00367

Measured 9d ago against content hash 8e459f3e8a0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

inversion 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • inversion — 100% identical, 0 lines differ
skills/strategy/inversion/SKILL.md · 530 lines

How it starts

The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inversion

"Invert, always invert." Apply Carl Jacobi's mathematical principle and Charlie Munger's investing wisdom to solve problems by thinking backward from failure.

When to Use This Skill

  • Goal setting - Define what would guarantee failure, then avoid it
  • Risk analysis - Identify what could destroy your project before starting
  • Decision making - Evaluate choices by examining their worst outcomes
  • Problem solving - When direct approaches aren't working, reverse the question
  • Strategy development - Find competitive advantages by avoiding common mistakes
  • Personal development - Identify habits and behaviors that guarantee failure

Methodology Foundation

Aspect Details
Source Carl Gustav Jacob Jacobi (1804-1851), mathematician; Charlie Munger, investor
Expert Munger credits Jacobi: "Invert, always invert" (from "man muss immer umkehren")
Core Principle Many problems are best solved backward. Instead of asking "How do I succeed?", ask "What would guarantee failure?" then avoid those things.

What Claude Does vs What You Decide

Claude Does You Decide
Structures content frameworks Final messaging
Suggests persuasion techniques Brand voice
Creates draft variations Version selection
Identifies optimization opportunities Publication timing
Analyzes competitor approaches Strategic direction

What This Skill Does

  1. Reveals hidden risks - Surfaces dangers invisible when thinking forward
  2. Simplifies complex problems - Failure paths are often clearer than success paths
  3. Prevents catastrophic mistakes - Avoidance is easier than achievement
  4. Improves decision quality - Forces consideration of downside scenarios
  5. Unlocks creative solutions - Reverse framing reveals new approaches

How to Use

Invert a Goal

Apply Inversion to this goal:
[describe your goal]

What would GUARANTEE failure? What should I avoid at all costs?

Read the full file on GitHub · 530 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. 9d ago First seen · 530 lines · 96 tokens per session scan A 8e459f3e8a0c

Subscribe to this mod's changes

inversion is a skill published in the GitHub repository guia-matthieu/clawfu-skills (149 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 3,668 once invoked, about $0.0005 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

debugging

Apply when diagnosing a bug, reproducing a failure, or performing root cause analysis. Covers systematic isolation, binary search, logging strategy, and hypothesis-driven investigation.

sordi-ai/skill-everything · 35 tokens

ast-grep

Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.

code-yeongyu/oh-my-openagent · 61 tokens

lcx-doctor

Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install…

code-yeongyu/oh-my-openagent · 93 tokens

lsp

Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.

code-yeongyu/oh-my-openagent · 27 tokens

ads-performance-analytics

How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…

rampstackco/claude-skills · 147 tokens

paid-media-strategy

A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media…

rampstackco/claude-skills · 142 tokens