Skip to main content
command CX Codex

inversion — Claude Code command: solve backwards

A command that applies inversion thinking: instead of asking “how do I succeed”, it asks “what guarantees failure” and builds a plan by avoiding those traps. Surfaces risks that optimistic planning misses.

MIT ★ 1,988 updated 2026-04-01

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resources
Open on GitHub

What inversion does

Inversion thinking flips the approach to problem-solving on its head. You state your goal, the command uncovers every way it could fail, then proposes concrete strategies to avoid each one. The result is a clear list of what never to do and a path to success through risk minimization.

The command works with a goal from the argument or analyzes the current conversation context. The process spans five steps: state the goal, invert the question to failure modes, list all ways things could go wrong, identify avoidance strategies for each, and build a success plan. Output is structured with goal headers, explicit failure modes with actions, an anti-goals checklist, and assessment of remaining risks.

What it helps with

  • uncover hidden risks in a project plan
  • avoid common pitfalls when designing a system
  • build strategy by identifying what guarantees failure
  • establish clear boundaries for what not to do

Example prompts for the agent

  • Apply inversion to designing an API that scales
  • What would guarantee our market launch fails?
  • /inversion the report needs to be ready in a week

How to install inversion

1Plugin marketplace

/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resources

2Manually: put the files in place

.claude/commands/inversion.md

Call it with /inversion. For all projects use ~/.claude/commands/

Questions about inversion

How do I install inversion in Claude Code?

Run /plugin marketplace add glittercowboy/taches-cc-resources, then /plugin install taches-cc-resources@taches-cc-resources. The command becomes available as /inversion.

What does the inversion command do?

It applies inversion thinking to your task: identifies every way things could fail, suggests strategies to avoid those failures, and builds a success plan grounded in risk elimination.

Can I use inversion without an argument?

Yes, it will analyze your current discussion context. Pass an argument to apply inversion to a specific goal or problem.

Source text

inversion.md · MIT
---
description: Solve problems backwards - what would guarantee failure?
argument-hint: [goal or leave blank for current context]
---

<objective>
Apply inversion thinking to $ARGUMENTS (or the current discussion if no arguments provided).

Instead of asking "How do I succeed?", ask "What would guarantee failure?" then avoid those things.
</objective>

<process>
1. State the goal or desired outcome
2. Invert: "What would guarantee I fail at this?"
3. List all failure modes (be thorough and honest)
4. For each failure mode, identify the avoidance strategy
5. Build success plan by systematically avoiding failure
</process>

<output_format>
**Goal:** [what success looks like]

**Guaranteed Failure Modes:**
1. [Way to fail]: Avoid by [specific action]
2. [Way to fail]: Avoid by [specific action]
3. [Way to fail]: Avoid by [specific action]

**Anti-Goals (Never Do):**
- [Behavior to eliminate]
- [Behavior to eliminate]

**Success By Avoidance:**
By simply not doing [X, Y, Z], success becomes much more likely because...

**Remaining Risk:**
[What's left after avoiding obvious failures]
</output_format>

<success_criteria>
- Failure modes are specific and realistic
- Avoidance strategies are actionable
- Surfaces risks that optimistic planning misses
- Creates clear "never do" boundaries
- Shows path to success via negativa
</success_criteria>

© Lex Christopherson · MIT · glittercowboy/taches-cc-resources

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

From the same set48

The whole set →
audit-skill audit-skill is a Claude Code command that checks a skill against YAML, XML, and progressive disclosure requirements before structural changes or publication. CX Codex +1 ★ 1,988repo stars 5-whys 5-whys runs the five whys technique on the problem you hand it and returns a root cause with one action to take. Useful when a bug keeps coming back after a fix. CX Codex +1 ★ 1,988repo stars first-principles first-principles deconstructs problems down to irreducible truths, removes conventions, and designs solutions from the ground up. CX Codex +1 ★ 1,988repo stars one-thing one-thing is a Claude Code command that picks one action with the greatest effect on the rest of a goal. Run it with a goal or let it use the current discussion. CX Codex +1 ★ 1,988repo stars via-negativa via-negativa applies the principle of subtraction to your code, features, or plans, identifying bloat to cut rather than adding new complexity. CX Codex +1 ★ 1,988repo stars occams-razor The occams-razor command weighs competing explanations against the facts and removes unsupported assumptions. Use it when a bug or decision has several plausible causes. CX Codex +1 ★ 1,988repo stars pareto pareto ranks the factors behind a decision by impact, keeps the few that carry most of the result and names the rest as safe to defer. CX Codex +1 ★ 1,988repo stars 10-10-10 10-10-10 evaluates choices across three distinct horizons: 10 minutes, 10 months, and 10 years. Spot tensions between immediate friction and lasting outcomes. CX Codex +1 ★ 1,988repo stars

Project sponsors

Companies that keep this analytics open