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-formsgit 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-forms)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-forms"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-forms/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-forms"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-forms.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 | $0.00081 | $0.03065 |
| Opus 5.5 | $0.00032 | $0.01226 |
| Sonnet 5.5 | $0.00016 | $0.00613 |
| Haiku 4.5 | $0.00008 | $0.00307 |
Grade A, and why
canon-forms 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Forms
Forms are the highest-stakes interface in any product. A confusing form costs conversions in marketing, costs data in apps, and costs trust everywhere. Most form failures are predictable.
Quantified Rules
Field Structure
<div class="field">
<label for="email">Email address</label>
<input
id="email"
name="email"
type="email"
autocomplete="email"
required
aria-describedby="email-hint"
/>
<span id="email-hint" class="hint">We'll never share your email.</span>
</div>
| Element | Required | Reason |
|---|---|---|
<label> with for |
Yes | Click target + screen reader |
id matching for |
Yes | WCAG 1.3.1 |
name |
Yes (for submission) | Server identification |
type |
Yes | Native validation + mobile keyboard |
autocomplete |
Yes (where applicable) | Browser fill, password managers |
required |
If required | Native validation |
aria-describedby |
If hint or error | SR announces context |
Label Placement
| Placement | When | Source |
|---|---|---|
| Above input (block) | Default. Best scan speed and mobile-friendly. | Nielsen Norman |
| Inline left | Settings panels with short fixed labels | Acceptable |
| Floating label | Material 3 style | OK; preserve label always-visible at zoom |
| Placeholder as label | Never | WCAG 3.3.2 violation |
Default to labels above inputs. Closer scan path, more mobile space, easier to align.
Label-to-Input Gap
4–8px between label and its input.
Less = cramped. More breaks proximity grouping (Gestalt).
Field-to-Field Gap
16–24px between fields.
Tighter feels rushed. Wider breaks form rhythm.
Input Sizing
| Property | Value | Source |
|---|---|---|
| Height | 44–48px (touch) | iOS HIG, Material 3 |
| Padding | 12px V, 16px H | Material 3 |
| Font-size | 16px minimum on mobile | Below 16px triggers iOS zoom-on-focus |
| Border | 1px solid, contrast >= 3:1 | WCAG 1.4.11 |
| Border radius | 4–8px | Match other components |
| Min width | 200px (single-line) | Usability |
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 · 325 lines · 81 tokens per session scan A 73d92a80d4e9
canon-forms is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 81 tokens to every session and 3,065 once invoked, about $0.0003 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 2026-08-31.
canon-forms compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-formsDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 81 | 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 |