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/noisy/noisy-coding/dashboard-design-languagenpx skills add noisy/noisy-coding --skill dashboard-design-languagegit clone --depth 1 https://github.com/noisy/noisy-codingWrote 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/noisy/noisy-coding/dashboard-design-language)<a href="https://agentmods.dev/skills/noisy/noisy-coding/dashboard-design-language"><img src="https://agentmods.dev/badge/skills/noisy/noisy-coding/dashboard-design-language.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 | $0.00066 | $0.00802 |
| Opus 5 | $0.00033 | $0.00401 |
| Sonnet 5 | $0.00013 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
dashboard-design-language 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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboard design language
Decisions made deliberately (2026-07-21 session, with Krzysztof calling each one) — not derivable from the code alone. New UI must speak this language; deviations are a conversation, not a default.
Color semantics — one meaning per color, everywhere
- red — muting and errors, nothing else. All mute signals are red and share the alarm look (MUTE MIC, muted portrait wash, muted tab glyphs). Never use red for a status like "waiting".
- amber — messages waiting / degraded-but-working.
- green — speaking right now, and good news (update available).
- violet — agent working/thinking. Always via
var(--violet)/color-mix(in srgb, var(--violet) N%, transparent)— never hardcoded rgba; retinting must stay a one-variable edit inhud.css. - cyan — structure, chrome, resting text. The neutral of this UI.
The fixed-slot rule
A state change NEVER changes an element's size. Status glyphs render
inside a fixed-size slot (tab statusslot); label swaps get a min-width
sized for the longest label (MUTE/MUTED button); hover affordances (tab
✕) are overlays that reserve or overlay space. If toggling something
makes neighbors shift, it's a bug.
Blink rules
- Only the LABEL/color pulses — the plate/background stays rock solid.
- The dim phase stays readable: a pulse, not a blackout (≥ ~0.5 opacity or a dimmer color, tuned by eye).
- All mute-related blinking shares the cadence:
1.6s step-end infinite.
Overlay, don't push
Anything that expands (voice-picker list, dropdowns, badges) overlays on
the z-axis over what's below — column heights never jump. Solid opaque
backdrop (--panel-solid) + shadow so it reads as a layer.
Layout architecture
Conversation-scoped things (log, telemetry strip, catch-up button, persona rail: portrait + character + session ring) live INSIDE the conversation frame, below the folder tabs. Machine-global things (mic controls, spectrum, system state, settings, mute-all) live in the left column or the header. The telemetry/catch-up width = the bubbles column only, never under the rail.
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.
- 4d ago First seen · 73 lines · 66 tokens per session scan A b272fedc53f9
dashboard-design-language is a skill published in the GitHub repository noisy/noisy-coding (7 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 802 once invoked, about $0.0003 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 skills, from other repositories
start-talking
Start and run an explicit, interactive Cadence Code conversation with Codex or Antigravity using fully local speech input and output. Use only when the user explicitly invokes $start-talking, /start-talking, or asks to start talking with Cadence Code.
jump-in
Interrupt an active Cadence Code conversation and add fresh spoken guidance to the current Codex or Antigravity task. Use only when the user explicitly invokes $jump-in or /jump-in after stopping the current host turn.
voice-settings
Choose Cadence Code's local speech and transcription models from the Codex or Antigravity UI. Use only when the user explicitly invokes $voice-settings, /voice-settings, or asks to open Cadence Code settings.
wrap-up
End an active Cadence Code conversation cleanly and release its local speech models. Use only when the user explicitly invokes $wrap-up, /wrap-up, or asks to wrap up the voice conversation.
speech-expert
Expert guide for speech-mcp - TTS, local/streaming STT, barge-in, wake word, voice command bus, and provider selection.
live-voice-agent
Use Live Voice Agent for gated Korean/English voice. Wake is 헤이 자비스.