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.
npx agentmods add skills/pillip/claude-dev-kit/uiuxnpx skills add pillip/claude-dev-kit --skill uiuxgit clone --depth 1 https://github.com/pillip/claude-dev-kitWhat 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 | $0.00039 | $0.12640 |
| Opus 5 | $0.00019 | $0.06320 |
| Sonnet 5 | $0.00008 | $0.02528 |
| Haiku 4.5 | $0.00004 | $0.01264 |
Grade A, and why
uiux 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.
How it starts
The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kit Preamble — uiux
Kit Script Root
Kit root: ${CLAUDE_PLUGIN_ROOT}
- Absolute path above → plugin install (substituted at load time; no project
scripts/dir): prefix every kit script command with it, e.g.bash <kit-root>/scripts/checkpoint.sh …. Absolute paths also work from worktrees. - Literal
${…}placeholder above → standalone layout: run commands as written.
Project Context Detection
Run these checks silently at the start. Use results to adapt behavior:
[ -f issues.md ]— if true, this project uses the sprint system. Respect issue numbering and STATUS.md.[ -f docs/sprint_state.md ]— if true and Status showsrunning, a sprint is active. Be aware of parallel work in worktrees.[ -f docs/prd_digest.md ]— if true, read it for quick project context before starting.
Kit Rules
- Verify
gh auth statusbefore any GitHub operation.
Prerequisites
/kickoffmust be run first so that the following files exist:docs/ux_spec.md(core input — IA, flows, screen inventory)docs/requirements.md(functional/non-functional requirements)docs/architecture.md(tech stack reference)
- The PRD file is supplementary reference. If kickoff outputs are missing, guide the user to run
/kickoff.
Algorithm
Phase 1 — Context Gathering
- Read kickoff outputs (required):
docs/ux_spec.md— extract screen inventory, IA, flowsdocs/requirements.md— identify UI elements from functional requirementsdocs/architecture.md— confirm tech stack, API endpoints
- Read PRD (
$ARGUMENTSorPRD.md) as supplementary context. Ifdocs/prd_digest.mdexists, read it for quick PRD summary. - If
docs/ux_spec.mddoes not exist:- Stop and tell the user: "Kickoff outputs are missing. Please run
/kickoff PRD.mdfirst." - Exception: if the user explicitly wants to skip kickoff, proceed with PRD only (warn about limited context).
Caching rule: All documents read in Phase 1 (
docs/ux_spec.md,docs/requirements.md,docs/architecture.md, PRD) are reused across all subsequent Phases. Do not re-read the same file with the Read tool.
- Stop and tell the user: "Kickoff outputs are missing. Please run
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 569 lines · 39 tokens per session scan A de27ec30be33
uiux is a skill published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 39 tokens to every session and 12,640 once invoked, about $0.0002 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.
Other skills, from other repositories
vgpu-shaders
Decide whether a Next.js 16 project should reach for WebGPU at all, then wire vgpu in: the .wgsl loader (Turbopack/webpack), a "use client" canvas that survives SSR, a prefers-reduced-motion path the library omits, a headless render snapshot in CI. Non-visual uses too — compute shaders (compute/dispatch, storage…
write-tests
Write Vitest unit/integration tests OR Playwright e2e tests for an existing source file (server action, page, component, query). Reads the project's wired test framework from .workflow/meta.json#stack.test, follows the mocking patterns already present in vitest.setup.ts and any sibling test files. Use when the user…
add-wshcmd
Guide for adding new wsh commands to Wave Terminal. Use when implementing new CLI commands, adding command-line functionality, or extending the wsh command interface.
web-reading
Read complex or JavaScript-rendered web pages cleanly. When a plain URL fetch returns an empty shell, garbled HTML, or "enable JavaScript", re-fetch the page through Jina Reader (https://r.jina.ai/) to get rendered, LLM-ready Markdown. Keyless, no setup. Use whenever a fetched page looks broken or you need the real…
add-config
Guide for adding new configuration settings to Wave Terminal. Use when adding a new setting to the configuration system, implementing a new config key, or adding user-customizable settings.
create-view
Guide for implementing a new view type in Wave Terminal. Use when creating a new view component, implementing the ViewModel interface, registering a new view type in BlockRegistry, or adding a new content type to display within blocks.