design-conversation

design-conversation is a command for Claude Code from Owl-Listener/ai-design-skills. It costs 12 tokens per session (429 once invoked), scanned A, original, MIT.

A command for designing a complete conversation between a person and an AI for a product feature.

In plain words
What is it for?
Plan interviews, guided workflows, or other AI interactions, including when control passes between the person and the AI.
Why use it?
It helps turn a vague feature idea into a structured plan covering goals, needed information, interaction flow, input and output types, and failure handling.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the model-interaction-design plugin — 8 skills, 3 commands shipped together

Good fit Plan interviews, guided workflows, or other AI interactions, including when control passes between the person and the AI.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/owl-listener/ai-design-skills/design-conversation
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.

Clone the repo
git clone --depth 1 https://github.com/Owl-Listener/ai-design-skills

Made for: Claude Code.

Or install model-interaction-design, the plugin that ships this one along with the rest of its 8 skills, 3 commands.

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 design-conversation

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/design-conversation"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/design-conversation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 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 $0.00012 $0.00429
Opus 5 $0.00006 $0.00215
Sonnet 5 $0.00002 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured 11d ago against content hash 1e76d8bcd25d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-conversation 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 11d 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.

claude-plugin/model-interaction-design/commands/design-conversation.md · 46 lines

What it actually says

You are designing a human-AI conversation flow. Use only skills from the model-interaction-design plugin. Follow this process:

Step 1: Understand the Task

Using conversation-patterns, identify:

  • What is the user trying to accomplish?
  • What information does the AI need from the user?
  • What information does the user need from the AI?
  • What's the expected conversation length (2 turns or 20)?

Step 2: Choose the Dialogue Structure

Using conversation-patterns, select the appropriate structure:

  • Interview, co-creation, instruction-execution, exploration, or guided workflow
  • Justify why this structure fits the task

Step 3: Map Initiative

Using mixed-initiative-flow, define:

  • Who initiates the conversation?
  • Where does initiative shift from user to AI and back?
  • What triggers each handoff?
  • Create an initiative map showing control at each stage

Step 4: Design Modality

Using multimodal-orchestration, specify:

  • What modalities are used for input and output at each stage?
  • Where do cross-modal transitions happen?
  • What's the primary modality and what's supporting?

Step 5: Plan for Breakdown

Using conversation-patterns (repair sequences) and feedback-loops:

  • Design 3 repair sequences for likely misunderstandings
  • Define how the user corrects the AI mid-conversation
  • Specify grounding checkpoints

Step 6: Design Disclosure

Using progressive-disclosure:

  • What capabilities are revealed at conversation start?
  • What's revealed as the conversation progresses?
  • How does the AI teach the user what else it can do?

Output

Deliver a complete conversation design document:

  1. Conversation flow diagram (text-based) showing all turns
  2. Initiative map
  3. Modality specification per stage
  4. Repair protocol
  5. Disclosure plan
  6. 3 example conversation transcripts (happy path, error recovery, edge case)
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. 11d ago First seen · 46 lines · 12 tokens per session scan A 1e76d8bcd25d

Subscribe to this mod's changes

design-conversation is a command published in the GitHub repository Owl-Listener/ai-design-skills (172 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 429 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 2026-08-30.