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 huuanh20/awesome-ai-agent-skills --skill inversion-exercisegit clone --depth 1 https://github.com/huuanh20/awesome-ai-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/huuanh20/awesome-ai-agent-skills/inversion-exercise)<a href="https://agentmods.dev/skills/huuanh20/awesome-ai-agent-skills/inversion-exercise"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-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/huuanh20/awesome-ai-agent-skills/inversion-exercise"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-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 | $0.00023 | $0.00495 |
| Opus 5 | $0.00012 | $0.00247 |
| Sonnet 5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00049 |
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 10d 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 — 62 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 they 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 |
| Centralize configuration | Distribute configuration | Feature flags, per-tenant config |
| Synchronous request → response | Async command → event | Event-driven architecture |
Process
- List core assumptions — What "must" be true?
- Invert each systematically — "What if the opposite were true?"
- Explore implications — What would we do differently?
- Find valid inversions — Which actually work somewhere?
Example
Problem: Users complain the app is slow
Normal approach: Make everything faster (caching, optimization, CDN)
Inverted: Make things intentionally slower in some places
- Debounce search input (add latency → enable better results, fewer DB hits)
- Rate limit requests (add friction → prevent abuse, smooth load)
- Lazy load content (delay → reduce initial load time)
Insight: Strategic slowness can improve UX and system health
Red Flags You Need This
- "There's only one way to do this"
- Forcing a solution that feels wrong
- Can't articulate why the approach is necessary
- "This is just how it's done"
- Every solution feels like fighting the problem
Remember
- Not all inversions work — test boundaries
- Valid inversions reveal context-dependence
- Sometimes the opposite is the answer
- Question every "must be" or "always" statement
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.
- 10d ago First seen · 62 lines · 23 tokens per session scan A a4ed3faa2959
Inversion Exercise is a skill published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 495 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 2026-08-31.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
check-mcp-json
Safely review, triage, repair, and merge ToolSDK MCP Registry package JSON pull requests. Use when an agent needs to validate files under packages/, detect duplicate registry keys, classify community PRs, make authorized fixes on contributor branches, close invalid or duplicate PRs, or squash-merge approved PRs.
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
prompt-architect
Analyzes and improves prompts using 31 frameworks across 7 intent categories. Use when a user wants to improve, rewrite, structure, or engineer a prompt — including requests like "help me write a better prompt", "improve this prompt", "what framework should I use", "make this prompt more effective", or any prompt…
spark-video-cast
Scaffold and generate reference assets for characters (cast), locations (movie-set / set dressing), and key props — the three pillars of visual consistency in spark-video. Wraps bl image generate / edit for portrait creation. Use when adding new characters/locations/props or when costume/state changes are needed.
spark-video-screenwriter
Turn a user's premise into a structured screenplay (one scene at a time) for the spark-video pipeline. Wraps Shanyin Super Screenwriting Master when available — that upstream Shanyin SKILL is the single source of truth for craft when present.