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-navigationgit 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-navigation)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-navigation"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-navigation/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-navigation"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-navigation.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 | $0.00082 | $0.01782 |
| Opus 5.5 | $0.00033 | $0.00713 |
| Sonnet 5.5 | $0.00016 | $0.00356 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
canon-navigation 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Navigation
Navigation is a promise: where am I, where can I go, how do I get back. Break any of the three and the user is lost.
Structural rules
Every page must answer three questions visually and semantically:
- Where am I? — active state in the nav, breadcrumb or page title
- Where else can I go? — primary nav visible or reachable in one tap
- How do I go back? — browser back always works; "back" actions never leave them stranded
Top bar vs sidebar
| Pattern | Use when | Don't use when |
|---|---|---|
| Top bar | ≤ 7 top-level sections, marketing, simple apps | > 7 sections, deep hierarchies |
| Sidebar | Apps with 8+ sections or nested nav, dashboards | Marketing pages, content-heavy reads |
| Hybrid (top + left) | Product with global sections + workspace nav | Simple apps — overkill |
| Bottom tab bar (mobile) | Apps with 3–5 primary sections | Web-first experiences, > 5 sections |
Active state — not optional
Every nav item has two states at minimum: default and active. "Active" means "you are here." It must be unmistakable at a glance.
Active state options, in order of clarity:
- Filled background + contrasting text
- Left or bottom border in brand color (2–3px)
- Bolder weight + color shift
- Underline (text nav only)
Color shift alone is not enough — fails for color-blind users. Pair color with weight, underline, or background.
Sizing
| Element | Dimension |
|---|---|
| Top bar height | 56–72px (64px is the sweet spot) |
| Sidebar width (expanded) | 220–280px |
| Sidebar width (collapsed icon-rail) | 56–72px |
| Nav item height (desktop) | 36–44px |
| Nav item height (mobile, tap target) | ≥ 44px |
| Nav item horizontal padding | 12–16px |
| Gap between items | 2–4px (stack), 16–24px (horizontal) |
| Bottom tab bar height | 56px + safe-area-inset-bottom |
Mobile menu (hamburger)
Hamburger is acceptable but comes with costs. Known: 30–50% lower discoverability vs visible nav (Luke Wroblewski research).
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 · 193 lines · 82 tokens per session scan A 94097e053472
canon-navigation is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 82 tokens to every session and 1,782 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-navigation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-navigationDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 82 | 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 |