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/panda850819/verbs/uinpx skills add panda850819/verbs --skill uigit clone --depth 1 https://github.com/panda850819/verbsWhat 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 | $0.00085 | $0.00536 |
| Opus 5 | $0.00043 | $0.00268 |
| Sonnet 5 | $0.00017 | $0.00107 |
| Haiku 4.5 | $0.00009 | $0.00054 |
Grade A, and why
ui 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 3d 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.
What it actually says
UI
Native frontend tooling can render a surface; this skill adds a committed visual
direction, craft review, and rendered evidence. Load references/craft.md before
writing CSS, not after. A CJK gut-feel complaint (很傻 / 突兀 / 丑 / 乱) is taste, not a bug — keep the
word, name the defect, fix; do not send it to debug.
- Evidence over taste. A preference is not a finding. Name the observable defect and its user impact, then confirm it in the rendered surface. Keep a deliberate choice that meets the task, accessibility and acceptance contract.
- Keep ownership clear.
prototypeanswers an open visual question,uichooses and implements the direction,qaproves browser acceptance, andreviewchecks the code diff. Do not turn a visual preference into a code-review finding. - Fight your defaults. Your first draft is the AI-default — Inter, purple→blue gradient, centered hero
with two CTAs, a grid of identical cards. Lock one named direction, then scan the first screen against the
default-trap checklist in
craft.mdand replace what drifted. - Verify the render, not the source. Screenshot at 375px and 1280px in every shipped locale before "done". Wraps, overflow, and widows are invisible in code.
- Build past the happy path. States (loading/empty/error) and the shippability layer a visual pass
skips — 404, back-nav, form validation, skip-link, footer legal — are in
craft.md.
Done when the named direction passes the default-trap scan, required states are covered, every visual claim has rendered evidence, and 375px/1280px screenshots are captured for every shipped locale.
Everything else — fonts, CJK type, OKLCH, CSS bans, motion, spacing, content rules — is craft you cannot
derive: references/craft.md.
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.
- 3d ago First seen · 37 lines · 85 tokens per session scan A fa9b4432a810
ui is a skill published in the GitHub repository panda850819/verbs (5 stars, last pushed 10d ago), licensed MIT. It adds 85 tokens to every session and 536 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 2026-08-31.
Other skills, from other repositories
markstream-react
Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, next, or server entrypoint, import CSS correctly, choose between content and nodes, keep client boundaries safe, add renderer-local streamingComponents or htmlComponents, use…
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
nba
Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a project is between phases, the author asks what to do next, too many valid threads are open, or the work needs re-entry into frame, build, drive, re0-memo, hate, re0-work, or ship.
dependabot-review
Analyzes a Dependabot PR to determine what actually changed in each bumped package and whether those changes affect this repo. Reports changed APIs/methods, which doc pages use them, and the realistic probability of any visible impact on the docs site.
review-validation
Validate review findings from specialist agents by reading the actual repo file content and checking each finding for accuracy, applicability, and false positives.
markdown-exporter
Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.