A one-command delivery check for one design page. It runs a code-style check, reviews accessibility and design patterns, and captures a screenshot.

Use it for a single page or route when checking readiness for delivery. It checks items such as tap-target size, color contrast, landmarks, and image descriptions.

It brings the main pre-handoff checks into one pass/fail workflow so problems can be found before development receives the page.

ship-design — Skill for Claude Code and Codex by leefanv

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 leefanv/omit-design --skill ship-design

Clone the repo

git clone --depth 1 https://github.com/leefanv/omit-design

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leefanv/omit-design/ship-design.svg)](https://agentmods.dev/skills/leefanv/omit-design/ship-design)

Your own site

<a href="https://agentmods.dev/skills/leefanv/omit-design/ship-design"><img src="https://agentmods.dev/badge/skills/leefanv/omit-design/ship-design.svg" alt="Measured on agentmods" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 673 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.

Model	Per session	Once invoked
Fable 5.1	$0.00077	$0.00673
Opus 5	$0.00039	$0.00336
Sonnet 5	$0.00015	$0.00135
Haiku 4.5	$0.00008	$0.00067

Measured 8d ago against content hash bc18f16bb928, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ship-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 8d 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/ship-design/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ship-design — one-command delivery for a single page

When to trigger

"ship the orders/list page"
"is design/foo/bar ready?"
"review and capture "
The user finished editing a page and asks for a final check before handoff.

Do NOT trigger for batch audits across the whole repo → use audit-design instead.

Inputs

The user must specify one target. Accept any of:

A path: design/orders/list.tsx
A route name: orders/list
A bare name: list (only if unambiguous)

Pipeline (run in order, fail fast)

Step 1 — lint

Run omit-design lint <resolved-path>.
If any violation → stop here. Report the violations and recommend audit-design to fix. Pipeline aborts.

Step 2 — accessibility & pattern review

Delegate to audit-reviewer sub-agent (if available in .claude/agents/) scoped to the single file.
If audit-reviewer is missing, do the review inline: check tap-target sizes, color contrast, presence of OmHeader or equivalent landmark, alt text for images.
Warnings are non-fatal but must be surfaced.

Step 3 — screenshot capture

Ensure npm run dev is running (or start it in the background).
Visit http://localhost:5173/designs/<group>/<name>.
Capture full-page screenshot to .omit-design/captures/<group>__<name>.png.
If the dev server isn't reachable in 5s, skip with a warning — do not block on this.

Output format

# ship-design: <group>/<name>

✓ lint        (0 errors, 0 warnings)
✓ a11y review (<n> notes)
✓ capture     (.omit-design/captures/<group>__<name>.png)

Status: READY

Or:

✗ lint        (<n> errors) → run /audit-design first
- a11y review SKIPPED (lint failed)
- capture     SKIPPED (lint failed)

Status: BLOCKED

Counter-examples

Running steps in parallel — they're sequential because each gates the next.
Reporting "ready" with warnings hidden — surface every warning even on success.
Trying to "fix" lint issues automatically — that's audit-design's job; ship-design only reports.
Resolving an ambiguous name to "probably orders/list" without asking.

Read the full file on GitHub · 73 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.

8d ago First seen · 73 lines · 77 tokens per session scan A bc18f16bb928

Subscribe to this mod's changes

ship-design is a skill published in the GitHub repository leefanv/omit-design (54 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 673 once invoked, about $0.0004 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.

Design and UX Testing agentic-workflow ai-figma omit-design

ux-torture-test

Break a user interface under real-world conditions across responsiveness, hostile content, interaction states, accessibility, network failure, interruption, and complete user journeys, reporting observable user harm with evidence rather than aesthetic opinion. Use whenever the user wants to stress-test a UI, verify…

playbookTV/Ironclad · 108 tokens

ship-design