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 tslateman/duet --skill designgit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/design)<a href="https://agentmods.dev/skills/tslateman/duet/design"><img src="https://agentmods.dev/badge/skills/tslateman/duet/design/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/tslateman/duet/design"><img src="https://agentmods.dev/badge/skills/tslateman/duet/design.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 | $0.00062 | $0.00780 |
| Opus 5.5 | $0.00025 | $0.00312 |
| Sonnet 5.5 | $0.00012 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
design 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design as Intention
Overview
Design is choosing what to do and what to leave out. Every design decision — visual, structural, interactive — should be deliberate. Generic defaults are the enemy. The key is intentionality, not intensity.
Design Thinking
Before implementing, commit to a direction:
- Purpose — What problem does this solve? Who uses it?
- Tone — What should it feel like? (Minimal, bold, playful, austere, warm, precise, raw)
- Constraints — Technical limits, accessibility, performance
- Differentiation — What makes this memorable? What's the one thing worth getting right?
Bold maximalism and refined minimalism both work. Timid middle ground does not.
Visual Design
When building interfaces, fight generic AI aesthetics:
Typography
Choose distinctive, characterful fonts. Pair a display font with a refined body font. Avoid defaults (Arial, Inter, Roboto, system fonts). Every font choice signals intent.
Color
Commit to a cohesive palette. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes. Vary between light and dark — don't default to one.
Motion
Focus on high-impact moments. One well-orchestrated page load with staggered reveals creates more delight than scattered micro-interactions. Prioritize CSS-only solutions. Use scroll-triggering and hover states that surprise.
Composition
Unexpected layouts. Asymmetry. Overlap. Grid-breaking elements. Generous negative space OR controlled density — both work, but choose one.
Texture
Create atmosphere and depth. Gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows. Never default to flat solid backgrounds.
Never: Overused font families, purple-gradient-on-white, predictable card grids, cookie-cutter components. No two designs should converge on the same choices.
API Design
When designing interfaces between systems:
- Consistency — Same patterns everywhere. If one endpoint uses
create, don't useaddelsewhere - Least Astonishment — Every method does what its name suggests, nothing more
- Minimal surface — Expose only what callers need. You can add later but can't remove
- Fail fast — Report errors at the point closest to the mistake
- Self-documenting — If the interface needs a comment, the design needs work
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 86 lines · 62 tokens per session scan A 289fdc624f58
design is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 780 once invoked, about $0.0002 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.
Other skills, from other repositories
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
recipe-front-design
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.
recipe-front-adjust
Adjust an already-implemented UI in-session with verification against the design source.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
git-workflow
Manages branches, worktrees, atomic commits, and branch completion by merge, PR, preserve, or discard. Use when starting feature work that needs a branch or an isolated workspace, making commits during development, or finishing a development branch. Also use when the user says "set up worktree", "create PR", "finish…