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-constraint-hardness-testinggit 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-constraint-hardness-testing)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-constraint-hardness-testing"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-constraint-hardness-testing/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-constraint-hardness-testing"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-constraint-hardness-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.01107 |
| Opus 5 | $0.00032 | $0.00553 |
| Sonnet 5 | $0.00013 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
s4h-constraint-hardness-testing 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 12d 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.
Constraint Hardness Testing
Organisations accumulate phantom constraints — rules that were real once and calcified, or beliefs that were never tested, or someone's preference that got repeated until it sounded like policy. This skill separates genuine limits from assumed ones before any energy is spent working around or accepting them.
Your Process
Step 1: State the Constraint Write it exactly as it's been stated or assumed. Don't clean it up — the imprecision is often where the phantom lives.
Framing check: Confirm the specific constraint and the goal it is blocking before continuing. State what you've identified — the exact constraint as you understand it and the goal or action it prevents — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the constraint and the goal it blocks]. 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 situation than read; incorporate the correction before proceeding
Step 2: Source It Who said this constraint exists? When? Is the source a law or regulation, a signed contract, a technical impossibility, a leadership decision, a team preference, or unknown? The source determines the hardness ceiling.
Step 3: Consequence Test What actually happens if this constraint is violated? State the consequence concretely. If the answer is "I'm not sure" or "someone would be unhappy," the constraint is not hard. Distinguish real consequences (fine, contract breach, system failure) from assumed ones (pushback, awkwardness, political cost).
Step 4: Precedent Check Has anyone tried to change or violate this constraint before? What happened? No precedent often means no one has tested it — not that it can't be changed.
Step 5: Conditions Test Under what circumstances would this constraint not apply? A truly hard constraint has no exceptions. If you can find a scenario where it wouldn't hold, the constraint is softer than stated.
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.
- 12d ago First seen · 118 lines · 63 tokens per session scan A a053c6b9063a
s4h-constraint-hardness-testing is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,107 once invoked, about $0.0003 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 2026-08-30.
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…
smeac
Structure briefings as Situation, Mission, Execution, Administration/Logistics, Command/Communications.
aarrr-pirate-metrics
Measure startup/product growth across Acquisition, Activation, Retention, Referral, Revenue.