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/muminur/frontend-design-craft-skill/delightgit clone --depth 1 https://github.com/Muminur/frontend-design-craft-skillWrote 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/muminur/frontend-design-craft-skill/delight)<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/delight"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/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 5.1 | $0.00007 | $0.00417 |
| Opus 5 | $0.00003 | $0.00209 |
| Sonnet 5 | $0.00001 | $0.00083 |
| Haiku 4.5 | $0.00001 | $0.00042 |
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 6d 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.
What it actually says
/delight
Add one — at most two — memorable moments to an otherwise polished interface. Restraint is the entire point. Delight applied everywhere is noise.
Target
$ARGUMENTS
Rules
- One delight per surface, maximum. A landing page gets one moment. A product UI gets at most one delight in the entire app.
- Tied to a meaningful action. First success, completion, milestone — not "page loaded" or "user scrolled."
- Skippable. Never block the user. If the animation is 800ms, the user can still proceed during it.
- Cultural awareness. Confetti reads as celebration in some contexts and as alarm in others. Sound is rarely appropriate by default.
Candidate moments
| Surface | Worth a delight |
|---|---|
| First sign-up complete | Subtle confetti or a satisfying state-change of the success badge |
| First task created / sent / shipped | Brief celebratory micro-interaction tied to the action |
| Empty state | A small custom illustration with personality, not a default empty box |
| 404 page | Often a good place to be more expressive than the rest of the site |
| Hero scroll moment | One scroll-triggered moment per page, max |
| Hover on the primary CTA | Subtle magnetic effect or color shift with character |
Anti-delights to remove
- Confetti on every form submit
- Bouncing emojis
- Glitch effects on text
- Mouse-trail animations
- Auto-playing sound
- Animated cursors
Output
## Delight added
**Moment:** [where, what]
**Trigger:** [user action]
**Duration:** [ms]
**Skippable:** [how]
**Reduced-motion fallback:** [what happens]
Confirm with the user before adding anything they did not specifically ask for.
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.
- 6d ago First seen · 54 lines · 7 tokens per session scan A e7365d4e47b5
delight is a command published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 417 once invoked, about $0.0000 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.