design-prompt

design-prompt is a command for Claude Code from Owl-Listener/ai-design-skills. It costs 10 tokens per session (444 once invoked), scanned A, original, MIT.

A command for writing a structured system prompt, the instruction set that guides an AI feature's behaviour and responses.

In plain words
What is it for?
Use it to define requirements and constraints, organise prompt sections, and add examples for normal and unusual requests.
Why use it?
It turns vague product requirements into explicit rules about the AI's role, limits, output, tone, and quality.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the prompt-architecture plugin — 7 skills, 3 commands shipped together

Good fit Use it to define requirements and constraints, organise prompt sections, and add examples for normal and unusual requests.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/owl-listener/ai-design-skills/design-prompt
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 prompt-architecture, the plugin that ships this one along with the rest of its 7 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-prompt

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/owl-listener/ai-design-skills/design-prompt"><img src="https://agentmods.dev/badge/commands/owl-listener/ai-design-skills/design-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 444 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 $0.00010 $0.00444
Opus 5 $0.00005 $0.00222
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00044

Measured 12d ago against content hash 7aaad593106f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-prompt 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.

claude-plugin/prompt-architecture/commands/design-prompt.md · 52 lines

What it actually says

You are designing a system prompt. Use only skills from the prompt-architecture plugin. Follow this process:

Step 1: Define Requirements

  • What is this AI feature for?
  • Who are the users?
  • What should the AI do? What should it NOT do?
  • What output format and quality is expected?

Step 2: Structure the Prompt

Using system-prompt-structure:

  • Write the Identity and Role section
  • Write the Context and Knowledge section
  • Write the Behavioral Rules section
  • Write the Output Specifications section
  • Ensure sections are clearly separated and ordered by importance

Step 3: Design Constraints

Using constraint-specification:

  • Define format constraints (output structure, required fields)
  • Define length constraints (word count ranges, section proportions)
  • Define content constraints (topics to include/exclude, source restrictions)
  • Define tone constraints (formality, voice, audience)
  • Define quality constraints (accuracy, completeness, actionability)
  • Establish constraint priority hierarchy

Step 4: Add Examples

Using few-shot-patterns:

  • Create 2-3 input-output examples demonstrating ideal behavior
  • Include one common case and one edge case
  • Ensure examples are high quality and consistent with the constraints

Step 5: Design Context Integration

Using context-engineering:

  • Define where retrieved context will be injected
  • Specify context selection criteria
  • Allocate the context budget across sections
  • Design the information architecture within the prompt

Step 6: Plan for Iteration

Using prompt-versioning:

  • Document the rationale for key design decisions
  • Define test cases for evaluating the prompt
  • Establish the review and deployment process

Output

Deliver a complete system prompt package:

  1. The system prompt itself (ready to use)
  2. Prompt design rationale document
  3. Constraint specification
  4. Example library (2-3 examples)
  5. Context integration specification
  6. Test cases for validation
  7. Version notes (v1.0)
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 · 52 lines · 10 tokens per session scan A 7aaad593106f

Subscribe to this mod's changes

design-prompt is a command published in the GitHub repository Owl-Listener/ai-design-skills (172 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 444 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.