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-tabsgit 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-tabs)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-tabs"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-tabs/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-tabs"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-tabs.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 | $0.00086 | $0.02237 |
| Opus 5.5 | $0.00034 | $0.00895 |
| Sonnet 5.5 | $0.00017 | $0.00447 |
| Haiku 4.5 | $0.00009 | $0.00224 |
Grade A, and why
canon-tabs 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Tabs
Tabs group related views that share the same page scope. Users switch between them to see alternate views of the same thing. Not a substitute for navigation.
When tabs are appropriate
| Appropriate | Not appropriate |
|---|---|
| Same entity, different views (Profile: Overview, Posts, Followers) | Unrelated pages |
| Filtering by category within a single view (All, Active, Archived) | Forms split across tabs |
| Settings organized into groups | Multi-step workflows (use stepper) |
Forms in tabs are almost always wrong. Users might submit without visiting a tab, or fill one and lose it on switch.
Multi-step processes aren't tabs. Linear flows use a stepper, not tabs.
Max tab count
| Count | OK? |
|---|---|
| 2–4 tabs | Ideal |
| 5–7 tabs | OK if labels are short |
| 8+ tabs | Redesign — use a sidebar or dropdown |
If tabs start overflowing the container, either the tabs are too many or the container is too narrow. Fix the cause, not the symptom.
Tab styles
| Style | Use |
|---|---|
| Underline tabs | Default for most UIs. Active tab has bottom border. |
| Filled / pill tabs | Segmented controls, mobile-native feel |
| Outlined tabs | Less common; works in dense dashboards |
| Icon + label tabs | When icons help scanning |
| Icon-only tabs (mobile tab bar) | 3–5 primary destinations (see canon-navigation) |
Underline tabs are the web default. Pill tabs often signal "filter control" more than navigation.
Active state — not optional
Active tab is unmistakable at a glance. Combine signals:
- Position (underline below, or filled background)
- Weight shift (medium → semibold on active)
- Color change (muted → strong on active)
Color alone fails colorblind users. Always pair.
Active text contrast ≥ 4.5:1. Inactive text contrast ≥ 4.5:1 — tabs are text, not decoration. "Inactive looks disabled" is a bug, not a style.
Keyboard behavior — WAI-ARIA tab pattern
This pattern is strict. Follow it exactly.
| Key | Behavior |
|---|---|
| Tab | Move focus into the tab list (focuses the active tab), then past it to the panel |
| Shift+Tab | Reverse |
| Arrow Right / Left (horizontal tabs) | Move focus between tabs, activating on focus (automatic) or on Enter (manual) |
| Arrow Up / Down (vertical tabs) | Same, along the vertical axis |
| Home | First tab |
| End | Last tab |
| Enter / Space | (Manual activation only) Activate the focused tab |
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 · 243 lines · 86 tokens per session scan A e955ec6faa65
canon-tabs is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 86 tokens to every session and 2,237 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 2026-09-03.
canon-tabs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-tabsDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 86 | 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 |