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 human-avatar/skills-for-humanity --skill s4h-play-worst-case-reversalgit clone --depth 1 https://github.com/human-avatar/skills-for-humanityWrote 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/human-avatar/skills-for-humanity/s4h-play-worst-case-reversal)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-play-worst-case-reversal"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-play-worst-case-reversal/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/human-avatar/skills-for-humanity/s4h-play-worst-case-reversal"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-play-worst-case-reversal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 51 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00082 | $0.01218 |
| Opus 5 | $0.00041 | $0.00609 |
| Sonnet 5 | $0.00016 | $0.00244 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
s4h-play-worst-case-reversal 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Play: Worst-Case Reversal
Direct brainstorming produces cautious, socially acceptable ideas. Designing the worst possible version removes the social cost of being wrong and unlocks the honest list of everything that actually fails — which, when reversed, becomes the most direct path to the design requirements that matter. The technique works because the worst-possible list is easy: everyone knows how to fail. The reversals do the serious work.
Your Process
Step 1: State the Design Challenge What are you designing, building, or solving? Be specific about the intended outcome — what would success look like if it worked?
Framing check: Confirm the specific design challenge before continuing. State what you've identified — the actual thing being designed and what success looks like — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the design challenge and its intended outcome]. Is that right?"
- Header: "Framing"
- Options:
- Yes — proceed — framing is correct
- Adjust — one element is off; user will correct it before you continue
- Reframe — different challenge than read; incorporate the correction before proceeding
Step 2: Design the Worst Version Ask: how would you make this as bad as possible? What would guarantee failure, alienate users, destroy trust, waste resources, or produce the exact opposite of the intended outcome? Generate without filter or politeness. Aim for 8-12 specific ways to make it terrible.
Rules for this step:
- No self-censorship. The worse the better.
- Be specific, not vague. "Make users wait 10 minutes" not "be slow." "Never acknowledge errors" not "have bad error handling."
- Include the uncomfortable ones — the ones that reveal real tensions, ignored trade-offs, or problems the current design is quietly making. These are the most valuable entries.
- If it feels too harsh to say, say it. Those are usually the ones that generate the most useful reversals.
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.
- 9d ago First seen · 118 lines · 82 tokens per session scan A 24a5040d2922
s4h-play-worst-case-reversal is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,218 once invoked, about $0.0004 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
decision-making-under-pressure
Provides practical habits for making better decisions faster -- reframing problems before solving them, knowing when to stop deliberating, balancing intuition with analysis, resisting 'just this once' compromises, and breaking overthinking cycles. Use when facing a high-stakes choice with incomplete data, sensing that…
flow-state
Optimizes individual and team productivity using Csikszentmihalyi's flow state framework, covering the conditions for flow (clear goals, immediate feedback, challenge-skill balance), the four-stage flow cycle, and organizational flow design. Use when auditing personal or team focus time, diagnosing productivity loss…
stoic-right-action
Applies Stoic ethics of right action to entrepreneurial decision-making, covering the four cardinal virtues (courage, justice, temperance, wisdom), ethical leadership under pressure, and the discipline of choosing the harder right over the easier wrong. Use when facing ethical dilemmas in business, building a…
bakeoff
Turn one decision into a judged tournament of solutions, then pick the best. Given a problem, design choice, or a suggestion you want cross-verified, it generates diverse candidate solutions, auto-derives the evaluation dimensions for THAT problem (so you don't have to know what to score on), judges every candidate…
balanced-scorecard
Translate strategy into metrics across Financial, Customer, Internal Process, and Learning & Growth perspectives.
customer-journey-map
Visualize every touchpoint a customer has with a product or service — stages, actions, emotions, pain points, opportunities.