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-design-iterationgit 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-design-iteration)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-design-iteration"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-design-iteration/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-design-iteration"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-design-iteration.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 | $0.00076 | $0.01854 |
| Opus 5 | $0.00038 | $0.00927 |
| Sonnet 5 | $0.00015 | $0.00371 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
s4h-design-iteration 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 13d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design: Iteration
No design survives first contact with the real world intact. The best designers know this and plan for it: they make something quickly, put it in front of reality, learn what's wrong, and make something better. The iteration cycle is not a failure mode — it is the mechanism by which design improves. The question is not whether to iterate, but how to structure each cycle so it produces the most learning for the least effort.
Dieter Rams designed and redesigned Braun products over decades of close observation — not because the first version was wrong but because fit is discovered, not planned. Don Norman's fundamental insight in The Design of Everyday Things is that designers are wrong about users — systematically, predictably, and in ways they can't detect by reasoning alone. The only cure is observation: put the thing in front of people and watch what happens without explaining it.
This skill structures the iteration cycle. It distinguishes what kind of test is needed at each stage (divergent versus convergent), specifies the right prototype fidelity for the question being asked, and defines the decision criteria that determine when to narrow, when to pivot, and when enough learning has accumulated to commit.
Your Process
Step 1: State the Current Hypothesis Every prototype is a test of a hypothesis. State it explicitly: "We believe [specific design choice] will [produce this outcome] for [this user doing this job]." If the hypothesis is vague, the test will be uninformative. Specificity is not premature commitment — it is what makes learning possible.
Framing check: Confirm the design stage and the hypothesis being tested before continuing. State what you've identified — the design being iterated and the key question it needs to answer — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the hypothesis and stage]. 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
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.
- 13d ago First seen · 141 lines · 76 tokens per session scan A 3b06f57eaf7a
s4h-design-iteration is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,854 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 2026-08-30.
Other skills, from other repositories
customer-journey-map
Visualize every touchpoint a customer has with a product or service — stages, actions, emotions, pain points, opportunities.
double-diamond
Design problems with two diamond phases: Discover/Define (right problem), Develop/Deliver (right solution).
token-audit
Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…
codebase-index
Generate a pre-computed component index from a design system codebase — YAML infrastructure files containing a component inventory, relationship graph, and summary statistics that AI agents and MCP servers consume. This produces machine-readable index files in .ai/index/, NOT a health report or quality assessment.…
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
review-design
Review digital artifacts against the user’s task, creative direction, functional and accessibility requirements, and actual delivery medium. Inspect renders, native files, playback or interaction as appropriate; exercise relevant failure and recovery paths and report evidence-backed findings. Use for design review or…