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 skills add aziontech/webkit --skill webkit-microcopygit clone --depth 1 https://github.com/aziontech/webkitWrote 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.
[](https://agentmods.dev/skills/aziontech/webkit/webkit-microcopy)<a href="https://agentmods.dev/skills/aziontech/webkit/webkit-microcopy"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/webkit-microcopy/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.
<a href="https://agentmods.dev/skills/aziontech/webkit/webkit-microcopy"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/webkit-microcopy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.05153 |
| Opus 5.5 | $0.00000 | $0.02061 |
| Sonnet 5.5 | $0.00000 | $0.01031 |
| Haiku 4.5 | $0.00000 | $0.00515 |
Grade A, and why
webkit-microcopy 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 24d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: webkit-microcopy
Purpose
Interface copy is part of the design system, not a per screen decision. When one screen says "Pick a workload" and the next says "Choose an application", when a label carries a warning that belongs in a message, or when an em dash splices two sentences inside a toast, the product reads as assembled by different people, and the reader pays for it with attention.
This skill fixes three things, in priority order:
- Mechanics. Punctuation and capitalization are settled, not stylistic. The bans below are hard.
- Placement. Every kind of copy has one surface that owns it. A label names an input; it never explains, warns, or gives feedback. Explanation comes before the input that needs it.
- Terminology. One word per concept, across every surface where that concept appears.
Scope: strings the user reads inside Azion products. It does not govern docs, marketing pages, code comments, or commit messages. Copy is authored in English; translation follows the Azion brand glossary, and every rule here survives translation because none of it depends on a specific wording.
How to use
/webkit-microcopywhile building: apply the rules to every string you write, and place each string on the surface that owns it before styling anything./webkit-microcopy <file|screen>as a review: walk the seven sections in order and report each violation ascurrent → corrected, with the surface it should move to when placement is wrong.
Related: /webkit-ui-states owns how loading, empty, and error render and where request failures
go. /webkit-form owns field structure and validation timing. This skill owns the words on all of
them.
1. Mechanics: the hard bans
| Ban | Why | Instead |
|---|---|---|
Em dash and en dash (—, –) |
Splices two thoughts into one unreadable line, and reads as unfinished editing | A period, a comma, or a colon. Two sentences are two sentences |
Ampersand (&) |
Not a word; noise in a label | and |
| Parentheses in labels | Flattens hierarchy: the aside competes with the name of the field | Move the aside to the field description, or to a Message above the group |
| Bold inside running text | Emphasis mid sentence fights the typography scale and reads as shouting | One idea per sentence. If it deserves prominence it deserves its own heading or tag |
| Feedback or consequence in a label | The reader has to parse a warning while looking for the field name | Message before the inputs it governs |
| Exclamation marks and decorative emoji | Infrastructure product, technical register | State the fact |
please, sorry, oops, whoops |
Padding, and it apologizes instead of resolving | Say what happened and what to do next |
simply, just, easy, quick |
Tells the reader their difficulty is their fault | Delete the word; the sentence is already shorter |
| ALL CAPS for emphasis | Only the overline token and acronyms are uppercase | Sentence case |
| A colon ending a field label | The input already shows where the value goes | Version, never Version: |
... (three periods) |
Not an ellipsis | The single character …, and only for genuine in-progress state (Deploying…) |
| Copy that names a layout position | The position changes at other widths, and in a drawer or bottom sheet it is simply false | Name the thing, not where it sits (in Deployment settings, not on the right) |
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.
- 24d ago Changed · +12 lines 942349c0ce96
- 1mo ago First seen · 300 lines · 0 tokens per session scan A a20c856d7796
webkit-microcopy is a skill published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,153 tokens. 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
design-component
Design a UI component spec to the house quality bar — anatomy, variants, sizes, the 8 states, token mapping, and accessibility. Use when the user wants to design or document a component (button, input, tabs, toast, combobox, date picker, modal, etc.) at the spec level before or alongside code. For generating framework…
design-doctrine
The house rules for ANY design or UI work - the verification protocol (run the gate, never claim a number), the absolute no-emoji rule, token by intent, one shared theme, the eight states, one thing leads, and output completeness. Load this FIRST whenever building, reviewing, or theming a screen, component, or token…
design-screen
Design or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this for "design a landing page", "build a settings screen", "make me a website", "design the onboarding", "ออกแบบหน้าเว็บ", "ทำหน้า landing", "ออกแบบ UI", "ทำแอป". It runs the pipeline no single skill…
grill-me
Interrogate the brief before a line is built — ask only the questions whose answers change the work, and put every unasked decision on the record as a stated assumption.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
scaffold-project
Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.