dev-3.0: Skill for Claude Code

.claude/skills/ux-create-manifest/SKILL.md

ux-create-manifest is a skill for Claude Code from h0x91b/dev-3.0. It costs 58 tokens per session (2,316 once invoked), scanned A, original, Apache-2.0.

A skill that audits an existing web app and creates its first UX Bible: documentation of screens, actions, structure and design rules.

In plain words
What is it for?
Use it to document an app's user experience, information structure, actions and design-token policies in docs/ux/ files.
Why use it?
It provides a project-specific reference based on the code, rather than relying on generic UX advice or guesses.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

This is h0x91b/dev-3.0's own configuration. It tells Claude Code how to work on dev-3.0 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dev-3.0 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to h0x91b/dev-3.0. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/h0x91b/dev-3.0/main/.claude/skills/ux-create-manifest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/h0x91b/dev-3.0

Made for: Claude Code.

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 ux-create-manifest

README.md
[![agentmods](https://agentmods.dev/badge/skills/h0x91b/dev-3.0/ux-create-manifest/github.svg)](https://agentmods.dev/skills/h0x91b/dev-3.0/ux-create-manifest)
Your own site
<a href="https://agentmods.dev/skills/h0x91b/dev-3.0/ux-create-manifest"><img src="https://agentmods.dev/badge/skills/h0x91b/dev-3.0/ux-create-manifest/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 ux-create-manifest

Your own site · 80×15
<a href="https://agentmods.dev/skills/h0x91b/dev-3.0/ux-create-manifest"><img src="https://agentmods.dev/badge/skills/h0x91b/dev-3.0/ux-create-manifest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,316 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00058 $0.02316
Opus 5 $0.00029 $0.01158
Sonnet 5 $0.00012 $0.00463
Haiku 4.5 $0.00006 $0.00232

Measured 9d ago against content hash 6bbc57715bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ux-create-manifest 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ux_inventory.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/ux-create-manifest/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX Create Manifest

You are a principal-level product UX architect creating the project's initial UX architecture bible.

Use this skill when:

  • The repository has no docs/ux/PRODUCT_UX_BIBLE.md or docs/ux/ux-architecture.yaml.
  • The existing UX manifest is stale, shallow, or disconnected from the actual app.
  • The user asks for a UX bible, UX architecture, product UX manifest, IA manifest, surface model, action taxonomy, or baseline UX audit.

Non-negotiable goal

Create a trustworthy, project-specific UX manifest derived from the current repository. Do not write a generic UX manifesto. Do not invent product features. Every observed fact must cite file paths or code evidence. Every inferred rule must be marked as inferred. Every proposed improvement must be marked as proposed.

Default write scope

You may create or update only UX documentation unless the user explicitly requests implementation changes:

  • docs/ux/PRODUCT_UX_BIBLE.md (include the glossary as a section here — no separate glossary file)
  • docs/ux/ux-architecture.yaml
  • docs/ux/UX_DECISIONS.md (seeded, kept compact — see ux-principal's decision log diet)

The manifest records placement, architecture, and the project's own deltas — its real token classes, documented exceptions, and any override of a better-* rule. It does NOT restate general craft rules; those belong to better-accessibility, better-colors, better-typography, better-writing, better-layout, and better-ui. A quality-floor section that could have been written about any project is a section to delete.

If the project has a test budget on doc size (dev3: src/bun/__tests__/ux-docs-budget.test.ts), respect it — compact rather than raise it.

Never stamp a generated-looking header on a hand-authored file. No updated_at, no confidence, no source: derived_from_repository on content a human will keep editing: those fields go stale within weeks and then invite the next reader to delete the file as a disposable cache. Say what the file is and let git carry the dates.

Read the full file on GitHub · 154 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. 9d ago First seen · 154 lines · 58 tokens per session scan A 6bbc57715bcd

Subscribe to this mod's changes

ux-create-manifest is a skill published in the GitHub repository h0x91b/dev-3.0 (252 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 2,316 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 2026-08-30.

Related

Other skills, from other repositories

ui-mockup

Create UI mockups at three fidelity levels — ASCII wireframes for quick iteration, standalone HTML mockups for delivery with requirements, and live prototypes for interaction testing.

mvschwarz/openrig · 37 tokens

design-engineering

Apply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when building a component, animation, transition, hover or press state, modal, drawer, toast, or when polishing an interface so it feels right. Says "make this feel better", "add an…

rohitg00/pro-workflow · 82 tokens

ui-review

Retroactive visual audit of UI implementation with 1-4 scoring per dimension.

SienkLogic/plan-build-run · 19 tokens

design-process

Engineering design cycle covering requirements elicitation, specifications writing, constraint identification, iterative prototyping, and design communication. Spans the full loop from problem definition through ideation, analysis, prototyping, testing, and redesign. Includes morphological charts, TRIZ, Pugh matrices…

Tibsfox/gsd-skill-creator · 89 tokens

prototyping-fabrication

CAD fundamentals, 3D printing (FDM/SLA/SLS), CNC machining, workshop skills, rapid prototyping methodology, and testing of physical prototypes. Covers fidelity levels, material selection for prototypes, dimensional tolerancing, assembly planning, and the iterate-test loop. Use when building prototypes, selecting…

Tibsfox/gsd-skill-creator · 82 tokens

household-systems-design

Designing the household as an operating system. Covers room-function mapping, work-triangle analysis, storage topology, utility flow, and the Richards/Beecher lineage that treats the home as an engineered environment rather than a stage set. Use when planning a new kitchen, reorganizing a room, diagnosing friction in…

Tibsfox/gsd-skill-creator · 90 tokens