ai-interaction-design

ai-interaction-design is a skill for Codex from memi-design/design-skills. It costs 52 tokens per session (650 once invoked), scanned A, original, MIT.

A guide to designing workflows where people and AI share tasks, decisions, and actions. It covers what the AI may suggest, create, execute, or remember, and when a person must review the result.

In plain words
What is it for?
Use it when designing AI features that generate content, make recommendations, take actions, or store information about users.
Why use it?
It helps prevent unclear automation, hidden uncertainty, unwanted memory, and risky actions without consent or review.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it when designing AI features that generate content, make recommendations, take actions, or store information about users.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/memi-design/design-skills/ai-interaction-design
Install

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.

Any agent
npx skills add memi-design/design-skills --skill ai-interaction-design
Clone the repo
git clone --depth 1 https://github.com/memi-design/design-skills

Made for: Codex.

Wrote 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.

agentmods badge for ai-interaction-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/memi-design/design-skills/ai-interaction-design/github.svg)](https://agentmods.dev/skills/memi-design/design-skills/ai-interaction-design)
Your own site
<a href="https://agentmods.dev/skills/memi-design/design-skills/ai-interaction-design"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/ai-interaction-design/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.

agentmods 80×15 button for ai-interaction-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/memi-design/design-skills/ai-interaction-design"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/ai-interaction-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00650
Opus 5 $0.00026 $0.00325
Sonnet 5 $0.00010 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 12d ago against content hash 94309e153c33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-interaction-design 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.

skills/ai-interaction-design/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Interaction Design

Design the relationship between human judgment and model behavior. Do not hide uncertainty, imply deterministic capability, or automate consequential actions without appropriate review and control.

Inputs

Establish the user goal, model role, source data, tools and actions, consequence level, latency, memory behavior, privacy constraints, evaluation evidence, failure modes, and the person accountable for the outcome.

Workflow

  1. Define the automation boundary. Separate what the model may suggest, draft, decide, execute, and remember. Match autonomy to consequence, reversibility, observability, and user expertise.
  2. Set expectations. Explain what the system can do, what information it uses, important limitations, expected latency, and when human review is required.
  3. Design input and context. Show what context is included, allow correction, protect sensitive information, and avoid requesting data the task does not require.
  4. Design progressive output. Represent queued, retrieving, generating, tool-use, awaiting approval, completed, partial, and failed states. Preserve useful partial work when safe.
  5. Expose provenance and uncertainty. Attach sources to claims, distinguish retrieved facts from generated inference, communicate material uncertainty, and provide a path to inspect evidence.
  6. Keep outputs editable. Let users revise, compare, regenerate selectively, restore earlier versions, and understand what changed. Avoid all-or-nothing regeneration.
  7. Gate consequential actions. Preview scope, target, cost, and side effects before execution. Require confirmation at the last responsible moment and provide receipts, undo, or escalation.
  8. Design memory controls. Make remembered information visible, correctable, removable, scoped, and time-bounded. Do not make personalization depend on opaque retention.
  9. Handle failure. Distinguish unavailable tools, insufficient evidence, policy refusal, model uncertainty, timeout, and partial execution. Offer truthful recovery rather than generic retry loops.
  10. Evaluate the whole workflow. Measure task success, factuality, groundedness, calibration, harmful action rate, correction burden, latency, accessibility, trust, and subgroup effects.

Read the full file on GitHub · 44 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 12d ago First seen · 44 lines · 52 tokens per session scan A 94309e153c33

Subscribe to this mod's changes

ai-interaction-design is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 650 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 2026-08-31.

Related

Other skills, from other repositories

accessibility

Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is design), NOT test-runner setup (that is testing-web), NOT LCP/page-speed (that is…

ericrisco/rsc-harness · 86 tokens

motion-lexicon

Design, build, compose, implement, review, and contribute polished product interfaces with Motion Lexicon components and motion primitives. Use this skill when a user asks for a complete React page, landing page, dashboard, settings screen, or product surface in the Motion Lexicon visual language; asks what motion…

Ryan-yang125/motion-lexicon · 157 tokens

motion-craft

Use when an interface moves and the movement has to feel right — durations and easing, what must never animate, fixing motion that reads sluggish, cheap or janky, and reduced-motion. Web and native. NOT the visual system (that is design), NOT the graded critique (that is design-loop).

ericrisco/rsc-harness · 67 tokens

accessibility-compliance-accessibility-audit-v2

Accessibility Audit and Testing workflow skill. Use this skill when the user needs You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance and the operator should preserve the upstream…

diegosouzapw/awesome-omni-skills · 76 tokens

a11y-audit

Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…

greglas75/zuvo · 147 tokens

design-engineering

Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…

broomva/skills · 231 tokens