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 agentmods add commands/dragoon0x/canon/delightgit 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/commands/dragoon0x/canon/delight)<a href="https://agentmods.dev/commands/dragoon0x/canon/delight"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/delight.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00513 |
| Opus 5 | $0.00008 | $0.00257 |
| Sonnet 5 | $0.00003 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
delight 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 3d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/delight
Not "add sparkle emojis everywhere." Not "bounce the button on hover." Delight is what survives after everything else is correct.
Principle
Delight is earned after fundamentals are correct. If contrast fails or buttons are nouns, no amount of polish saves the interface. Fix those first.
What this does
- Verify the fundamentals pass:
canon-typography,canon-color,canon-spatial,canon-accessibility,canon-states,canon-ux-writing. - Only then, look for moments that reward attention:
- Empty states with personality: an illustration that fits the brand voice, not a generic cactus.
- Hover reveals: secondary info appears on hover for power users, always also accessible via keyboard.
- Smart defaults: the form pre-fills with context-appropriate guesses.
- Optimistic UI: the action looks instant; the network catches up.
- Progress with character: "Translating your manuscript from Latin..." beats "Loading...".
- Celebration, quietly: a single checkmark animation on success. Not confetti. Never confetti.
- Tactile feedback: subtle scale (0.98) on active press. Shadow deepens 1 level on hover. Nothing bigger.
- Every moment passes the "second use" test: does it still feel good the hundredth time, or does it turn into friction? If it wears out, cut it.
- Every moment honors
prefers-reduced-motion. Delight that gives someone a headache isn't delight.
Anti-patterns to reject
- Confetti on routine success.
- Autoplay sound.
- Lottie animations as loaders (they're often 500KB+ for three seconds of motion).
- Tooltips that reveal critical info (accessibility failure).
- Easter eggs buried in destructive flows.
- Sparkle trails on cursors.
- Bouncing CTAs to "grab attention."
Output
- 3–5 specific delight moments, with rationale per moment.
- Code for each.
- Reduced-motion fallback.
- Second-use test answer: "would I still smile at this after the hundredth time?"
Success criteria
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.
- 3d ago First seen · 48 lines · 16 tokens per session scan A 89f37627bc37
delight is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 513 once invoked, about $0.0001 per session on Opus 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.
Other commands, from other repositories
pm-status
Scan open PRs, report pipeline state, merge ready work to dev, and keep the staging promotion PR current.
review-pr
Fetch a pull request diff, run code-reviewer analysis, translate findings to owner voice, and post a single batched inline GitHub review.
codex-review
Run an adversarial review of the current branch via Codex (GPT-5.4). Default = direct Bash + thin + cheap; --verbose = wrapper-agent + 3x Opus burn.
halt-check
Smoke test — verify every hook and middleware respects the HALT kill switch. Advisory, read-only.
freeze
Activate the REA kill switch — writes .rea/HALT with a reason, blocking all governed tool calls until unfrozen.
review
Run the code-reviewer agent against the current branch's diff and produce structured findings.