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.
npx skills add PracticalSwan/agent-skills --skill inversion-exercisegit clone --depth 1 https://github.com/PracticalSwan/agent-skillsWrote 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.
[](https://agentmods.dev/skills/practicalswan/agent-skills/inversion-exercise)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/inversion-exercise"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/inversion-exercise/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.
<a href="https://agentmods.dev/skills/practicalswan/agent-skills/inversion-exercise"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/inversion-exercise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00930 |
| Opus 5 | $0.00012 | $0.00465 |
| Sonnet 5 | $0.00005 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
inversion-exercise 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inversion Exercise
Overview
Flip every assumption and see what still works. Sometimes the opposite reveals the truth.
Core principle: Inversion exposes hidden assumptions and alternative approaches.
Quick Reference
| Normal Assumption | Inverted | What It Reveals |
|---|---|---|
| Cache to reduce latency | Add latency to enable caching | Debouncing patterns |
| Pull data when needed | Push data before needed | Prefetching, eager loading |
| Handle errors when occur | Make errors impossible | Type systems, contracts |
| Build features users want | Remove features users don't need | Simplicity >> addition |
| Optimize for common case | Optimize for worst case | Resilience patterns |
Process
- List core assumptions - What "must" be true?
- Invert each systematically - "What if opposite were true?"
- Explore implications - What would we do differently?
- Find valid inversions - Which actually work somewhere?
Example
Problem: Users complain app is slow
Normal approach: Make everything faster (caching, optimization, CDN)
Inverted: Make things intentionally slower in some places
- Debounce search (add latency → enable better results)
- Rate limit requests (add friction → prevent abuse)
- Lazy load content (delay → reduce initial load)
Insight: Strategic slowness can improve UX
Red Flags You Need This
- "There's only one way to do this"
- Forcing solution that feels wrong
- Can't articulate why approach is necessary
- "This is just how it's done"
Remember
- Not all inversions work (test boundaries)
- Valid inversions reveal context-dependence
- Sometimes opposite is the answer
- Question "must be" statements
Cross-Client Portability
This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.
- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
- Claude Code: keep the folder in a local skills directory or a compatible plugin source.
- Codex: install or sync the folder into
$CODEX_HOME/skills/inversion-exerciseand restart Codex after major changes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed c34e150ca7b4
- 4d ago Changed 7f72e5ea6bc7
- 7d ago First seen · 107 lines · 24 tokens per session scan A 0e8066e1965a
inversion-exercise is a skill published in the GitHub repository PracticalSwan/agent-skills (14 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 930 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.
Other skills, from other repositories
evaluating-and-deciding
Covers the full arc from option evaluation through execution and post-decision learning: criteria weighting and the 'most important thing' discipline, high-fidelity and high-expertise information gathering, margin of safety as a buffer against being wrong, the irreversibility test for calibrating decision speed…
mk:elicit
Structured second-pass reasoning after code review or plan evaluation. Offers named reasoning methods (pre-mortem, inversion, red team, Socratic, etc.) to re-examine findings through a specific lens. Use after /mk:review verdict or any time deeper analysis is needed on an existing output. NOT for initial review (see…
invert
Flips constraints and beliefs to expose false walls and test plan robustness against inverted worldviews.
exercise-generator
A teaching-material skill that creates practice questions from a completed lesson chapter. It produces multiple-choice, fill-in-the-blank, short-answer, and hands-on tasks with answers and explanations.
meal-planner
Use when planning macronutrient targets, calculating daily calorie ranges, or building meal plans based on body type, activity level, and fitness goals.
body-composition
Use when assessing body fat percentage from skinfold measurements, calculating body density, or interpreting body composition results using Durnin-Womersley or Jackson-Pollock equations.