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-onboardinggit 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-onboarding)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-onboarding"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-onboarding/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-onboarding"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-onboarding.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 | $0.00074 | $0.00745 |
| Opus 5.5 | $0.00030 | $0.00298 |
| Sonnet 5.5 | $0.00015 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
canon-onboarding 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Onboarding
The best onboarding is the interface being obvious enough to not need onboarding. When that's not possible, teach in context, not upfront.
Onboarding hierarchy (best to worst)
- Self-evident UI — labels, layout, and flow are clear. No onboarding needed.
- Smart defaults — pre-fill the first project, pre-select common settings.
- Empty states with guidance — "No projects yet. Create one to get started."
- Contextual tooltips/coachmarks — appear when the user first reaches a feature.
- Checklist — "Complete your setup: ✓ Profile, ○ Team, ○ First project."
- Interactive walkthrough — step-by-step guide within the product.
- Video/tutorial modal — the fallback. Most users skip it.
Principles
- Earn before asking. Don't ask for preferences before the user has experienced value.
- Just-in-time over just-in-case. Explain the feature when the user encounters it, not 12 screens earlier.
- Progressive disclosure. Reveal complexity as users demonstrate readiness.
- Let users skip everything. Every tour, modal, and tooltip must have a clear dismiss.
- Never block the interface. Overlays and modals that prevent exploration are anti-onboarding.
Coachmarks
Small tooltips pointing to a UI element on first encounter.
- One at a time. Never 5 coachmarks on screen.
- Dismiss on click, after action, or after a few seconds.
- Don't re-show after dismissal (persist state).
- Position per
canon-tooltipsrules.
Checklists
Work well for multi-step setup (profile, invite team, connect integration).
- Show progress (2 of 5 complete).
- Mark completed items visually (checkmark, strikethrough).
- Lead with the easiest step (quick win builds momentum).
- Allow out-of-order completion.
- Collapse or dismiss after completion.
Anti-patterns
| Anti-pattern | Why it fails |
|---|---|
| 5-screen carousel before the product | Users skip or forget by screen 3 |
| Mandatory video on first visit | Most users close immediately |
| Covering the entire UI with overlay instructions | Users can't explore |
| Asking for 10 preferences before showing value | Premature commitment |
| Coachmarks that can't be dismissed | Trapped |
| Re-showing dismissed tours | Annoying, shows disrespect |
| No skip option anywhere | Hostile to returning users |
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 · 75 lines · 74 tokens per session scan A 41ad7c99e8ce
canon-onboarding is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 745 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-onboarding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-onboardingDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 74 | 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 |