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 Dragoon0x/canon --skill canon-ux-writinggit clone --depth 1 https://github.com/Dragoon0x/canonWrote 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/dragoon0x/canon/canon-ux-writing)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-ux-writing"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-ux-writing/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/dragoon0x/canon/canon-ux-writing"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-ux-writing.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 | $0.00090 | $0.02803 |
| Opus 5.5 | $0.00036 | $0.01121 |
| Sonnet 5.5 | $0.00018 | $0.00561 |
| Haiku 4.5 | $0.00009 | $0.00280 |
Grade A, and why
canon-ux-writing 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 2mo 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · UX Writing
Interface copy is design. A 4-word button label is a design decision. A confusing empty state breaks an otherwise polished product. The rules below produce copy that disappears into use.
Core Principles
- Verbs over nouns. Buttons describe actions: "Create account", not "Account creation".
- Specific over generic. "Send invoice" beats "Submit". "Email is required" beats "Invalid input".
- Active voice over passive. "We sent your invoice" beats "Your invoice has been sent".
- Plain words over jargon. "Sign in" beats "Authenticate". "Try again" beats "Retry operation".
- User's language over yours. "Posts" not "Resources" if your users say "posts".
- Sentence case over Title Case. Reads faster, feels modern. Use Title Case only for proper nouns and product names.
Button Labels
| Bad | Good |
|---|---|
| Submit | Send message / Create account / Save changes |
| OK | Got it / Continue / Done |
| Cancel | Cancel (this one is fine) / Discard / Keep editing |
| Click here | (link should describe destination) |
| Learn more | Read the security guide |
| Yes / No | Save changes / Discard |
| Continue | Continue to payment |
Rule: button label = verb + object when possible. "Save", "Save profile", "Save and continue".
Button Pairs (confirm/cancel)
| Context | Primary | Secondary |
|---|---|---|
| Saving | Save changes | Cancel |
| Discarding | Discard changes | Keep editing |
| Destructive | Delete project | Cancel |
| Confirming | Yes, sign me out | No, stay signed in |
Destructive actions always require explicit confirmation language. "Delete" alone, with the user already on a delete confirmation modal, is acceptable. "Delete project" is better.
Button Tone by Context
| Context | Tone |
|---|---|
| Marketing CTA | Bold, benefit-focused: "Start free trial" |
| App primary action | Direct, action-focused: "Save changes" |
| Destructive | Clear and confirming: "Delete forever" |
| Loading state | Present continuous: "Saving…", "Sending…" |
| Success state | Past tense: "Saved", "Sent" |
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.
- 2mo ago First seen · 291 lines · 90 tokens per session scan A 1e6826d38734
canon-ux-writing is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 90 tokens to every session and 2,803 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
canon-ux-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-ux-writingDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 90 | Claude Code, Codex |
| accessibilitydiegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | C | 119 | Claude Code, Codex |
| accessibilityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| accessibility-auditoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 29 | Claude Code |
| a11y-auditgreglas75/zuvo | Skill | 7 | 3d ago | MIT | A | 147 | Claude Code |
| axe-audittonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 47 | Claude Code |
| accessibility-compliance-accessibility-audit-v2diegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | A | 76 | Claude Code |