wireframe-prototyping

A method for sketching a simple screen layout and documenting how people use it, including successful, empty, error, and unusual cases.

In plain words
What is it for?
Use it to outline desktop or mobile screens, map user flows, draw text-based wireframes, add interaction notes, and define acceptance criteria.
Why use it?
It helps clarify what a screen must contain and how it should behave before detailed design or coding begins.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/soulcodex/agentic/wireframe-prototyping
Any agent
npx skills add soulcodex/agentic --skill wireframe-prototyping
Clone the repo
git clone --depth 1 https://github.com/soulcodex/agentic

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00062 $0.00807
Opus 5 $0.00031 $0.00404
Sonnet 5 $0.00012 $0.00161
Haiku 4.5 $0.00006 $0.00081

Measured 2d ago against content hash c53cbabfd1f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wireframe-prototyping 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 2d 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/ui/wireframe-prototyping/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wireframe Prototyping Skill

Step 1 — Clarify Scope

Before sketching, confirm:

  • Which screen or flow is being wireframed?
  • What device target: desktop, mobile, or both?
  • What is the primary user goal this screen must satisfy?
  • Are there existing designs or brand constraints to follow?

Step 2 — Identify User Flows

List the key flows the wireframe must cover:

  • Happy path (primary action the user takes)
  • Empty states (no data yet)
  • Error states (validation failure, network error)
  • Edge cases (long strings, many items in a list)

Step 3 — ASCII Wireframe

Sketch the layout using ASCII art. Use these conventions:

+------------------------+   ← container border
| Page Title             |   ← text
+------------------------+
| [ Search...          ] |   ← text input
| [ Button ]  [ Cancel ] |   ← buttons
+--------+---------------+
| Nav    | Main Content   |
| - Item |                |
| - Item | +------------+ |
|        | | Card Title | |   ← card
|        | | Subtitle   | |
|        | [ Action     ] |
|        | +------------+ |
+--------+---------------+
| Footer                  |
+------------------------+

Legend:
  [ text ]         ← button
  [ text...      ] ← text input
  < Option ▼ >    ← dropdown / select
  (•) Option       ← radio button
  [x] Label        ← checkbox
  ~~~              ← image / media placeholder

Produce a separate wireframe per breakpoint if mobile and desktop differ significantly.

Step 4 — Interaction Annotations

After each wireframe, add a numbered annotation list:

Interactions:
1. Clicking [ Search ] submits the search form → loads results in Main Content.
2. Empty state shows "No results found" with a [ Clear filters ] button.
3. Clicking a Card opens a detail drawer (slides in from the right).
4. < Option ▼ > dropdown filters results in real-time (no submit needed).
5. Error state shows an inline banner: "Something went wrong. [ Retry ]"

Step 5 — Figma / Excalidraw Handoff Notes

If handing off to a designer, note:

  • Spacing guidelines (e.g., 8-pt grid, 16 px section padding).
  • Component names to reuse from the design system (if known).
  • Any animation or transition intent (e.g., "drawer slides in 200 ms ease-out").
  • Responsive behaviour: how the layout reflows on smaller screens.

Read the full file on GitHub · 110 lines

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. 2d ago First seen · 110 lines · 62 tokens per session scan A c53cbabfd1f2

Subscribe to this mod's changes

wireframe-prototyping is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 807 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.