ux-wireframe

A command that turns a user-interface specification into a rough layout or wireframe. A wireframe is a simple screen plan showing structure and flow before detailed visual design.

In plain words
What is it for?
Use it to create low-detail UX artifacts from frontend specifications and, when configured, rough frames in Figma.
Why use it?
It gives the team something concrete to review before investing time in polished designs or frontend code.

Command

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 commands/rajconnects/founder-stack/ux-wireframe
Clone the repo
git clone --depth 1 https://github.com/rajconnects/founder-stack
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 687 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 $0.00059 $0.00687
Opus 5 $0.00030 $0.00344
Sonnet 5 $0.00012 $0.00137
Haiku 4.5 $0.00006 $0.00069

Measured yesterday against content hash e4d587e7abd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-wireframe 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 yesterday.

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.

workflow/commands/ux-wireframe.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the wireframe step of the UX design layer.

Arguments: $ARGUMENTS

Steps

  1. Resolve scope. Parse $ARGUMENTS. If empty or auto, read spec_roots.frontend then spec_roots.build_plans from .claude/project.json and pick the most recently modified spec file under those roots. Otherwise use the path/scope given. If no spec resolves, fail loudly: ux-wireframe requires a spec path or scope. Try /ux-wireframe auto if a recent frontend spec exists.

  2. Compute the scope slug. Slugify the scope label (or the spec's primary component name) for marker filenames: lowercase, alphanumerics + dashes only.

  3. Resolve config and inline. Read .claude/project.json once. Extract: spec_roots, design_system.components_spec, design_system.flow_spec, design_system.tokens, design_system.principles (may be null), design_system.figma.file_key, design_system.figma.screens, stack.frontend, stack.frontend_root. If stack.frontend is null, fail: ux-wireframe only runs for frontend specs (stack.frontend is null). If components_spec or flow_spec is null, fail: ux-wireframe requires components_spec and flow_spec paths.

  4. Launch ux-wireframer with a self-contained prompt containing: the resolved spec path, scope label and slug, the inlined config fields above, the --source reference (if any), and the --skip-when-trivial flag (if any). Do NOT ask the agent to re-read project.json.

  5. Print the agent output verbatim. Do not soften or reinterpret. The agent's output is the wireframe deliverable.

  6. Mark on success. If verdict is ARTIFACTS_PRODUCED, touch .claude/.ux-wireframe-passed-<scope-slug>. On ERROR, do not write the marker.

  7. Closing line. On success print: wireframe ready: review the [WIREFRAME] frames in Figma, then run /ux-mockup <scope>.

Notes

  • --skip-when-trivial is for one-line scopes that don't warrant Figma frames. The agent still extends components_spec / flow_spec and writes the marker.
  • The marker is gitignored and per-session. .claude/.ux-wireframe-passed-<scope-slug> is consumed by /ux-mockup as a hard prerequisite.
  • If design_system.figma.file_key is null, the agent skips Figma writes entirely and still produces the spec extensions.

Read the full file on GitHub · 31 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. yesterday First seen · 31 lines · 59 tokens per session scan A e4d587e7abd9

Subscribe to this mod's changes

ux-wireframe is a command published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 687 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.