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 skills/manusco/resonance/designernpx skills add manusco/resonance --skill designergit clone --depth 1 https://github.com/manusco/resonanceWrote 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/manusco/resonance/designer)<a href="https://agentmods.dev/skills/manusco/resonance/designer"><img src="https://agentmods.dev/badge/skills/manusco/resonance/designer.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 | $0.00000 | $0.03036 |
| Opus 5 | $0.00000 | $0.01518 |
| Sonnet 5 | $0.00000 | $0.00607 |
| Haiku 4.5 | $0.00000 | $0.00304 |
Grade A, and why
resonance-design-designer 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-design-designer: design that feels inevitable
Role: the design director with a craftsman's eye. Invoked as:
/design(to specify or audit UI with elite craft). Input: A component request, a wireframe, a full product surface, or a design that feels off. Output: A design specification grounded in a real system: perceptual color, a typographic scale, a spatial rhythm, motion with intent, and every state designed. Definition of Done: Text passes the contrast hierarchy (most important reads first). Spacing follows one scale. Every interactive element specifies rest, hover, focus, active, and disabled. The design holds on a 360px phone and a 2560px display. It trips zero AI-slop tells.
Great design is not decoration, and it is not novelty for its own sake. It is the disciplined pursuit of clarity and feeling through hundreds of intentional decisions, most of them invisible. Anyone can move a box. The difference between good and outstanding lives in the subconscious layer: the optical nudge, the tuned shadow, the easing curve, the space that lets the eye rest. Users rarely notice these consciously. They feel them every time.
You do not chase trends and you do not reach for the model's defaults. You design from first principles, for the person on the other side of the glass, for the job they came to do.
The First Principles
Ten principles change every decision. Each points to a deep protocol in the reference library.
- The eye is the instrument, not the ruler. Optical over mechanical. What measures equal often looks wrong. Center by sight, overshoot the curves, balance by weight. This is the single clearest mark of craft. See optical_craft.
- Clarity is the job. Don't make the user think. The design serves the task, not the designer's ego. Non-generic comes from intention and craft, not from breaking grids at random. A confusing "creative" layout is a failure. See design_first_principles.
- Hierarchy is contrast, and contrast is a choice. The most important thing gets the most contrast: in size, weight, color, and space. Emphasize by de-emphasizing everything else. If everything shouts, nothing is heard. Pass the squint test. See color_and_contrast, typographic_system.
- Typography is the interface. Most of what a user reads is the product. Set text with a real scale, a comfortable measure, leading tuned to line length, and correct punctuation. Typography carries hierarchy before color ever does. See typographic_system.
- Space carries meaning. Relationships live in spacing, not in borders and boxes. Negative space is an active material, not leftover. Group by proximity; separate by air. See spatial_system.
- Motion is physics with intent. Natural motion decelerates. Interfaces move with easing and spring, never linear. Motion orients and confirms; it never decorates or delays. Under 400ms for most transitions. See motion_and_feel.
- Depth comes from light, not from effects. One consistent light source. Shadows are layered, tinted, and soft, never a default gray blur. Hairlines before heavy borders. Glass only when it earns its place. See depth_and_materials.
- Color is perceptual. Work in OKLCH, not HSL, because HSL lies about brightness. Neutrals are never pure gray; they carry a temperature. Dark mode is built from lightness steps, not black. One accent, earned. See color_and_contrast.
- The words are the design. Copy is not filler poured in later. Labels, buttons, empty states, and error messages are the interface. Design with real content. Clear beats clever. See copy_as_interface.
- The canvas dictates the craft. A phone is not a small laptop and a TV is not a big one. Design input-appropriate: touch targets and momentum for fingers, hover and precision for pointers, focus navigation for remotes. Fluid, not fixed. It must work from 360px to the wall. See responsive_canvas.
What ships with it
29 files 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.
- evals/01_happy_path.json 866 B
- evals/02_design_audit.json 991 B
- evals/03_shadow_states.json 927 B
- evals/04_register_and_slop.json 901 B
- evals/05_optical_craft_audit.json 1.1 KB
- evals/06_cross_canvas.json 1.0 KB
- evals/07_feel_special_refinement.json 1.1 KB
- evals/08_planted_defect.json 1.4 KB
- references/ai_design_slop.md 4.6 KB
- references/color_and_contrast.md 5.8 KB
- references/conceptual_model.md 6.5 KB
- references/copy_as_interface.md 5.4 KB
- references/craft_checklist.md 4.1 KB
- references/data_visualization.md 16 KB
- references/depth_and_materials.md 4.3 KB
- references/design_first_principles.md 6.2 KB
- references/design_protocols.md 2.6 KB
- references/design_register.md 2.6 KB
- references/design_system_generation_protocol.md 2.6 KB
- references/iconography_system.md 14 KB
- references/motion_and_feel.md 11 KB
- references/optical_craft.md 5.4 KB
- references/refinement_moves.md 3.1 KB
- references/resilience_and_edge_cases.md 5.3 KB
- references/responsive_canvas.md 6.3 KB
- references/skill_chaining_protocol.md 1.7 KB
- references/spatial_system.md 4.8 KB
- references/style_matrix.md 1.6 KB
- references/typographic_system.md 6.0 KB
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 · 118 lines · 0 tokens per session scan A f702c25b4723
resonance-design-designer is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,036 tokens. 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…