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 OutlineDriven/odin-claude-plugin --skill designgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/design)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/design"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/design.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 83 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00046 | $0.02402 |
| Opus 5 | $0.00023 | $0.01201 |
| Sonnet 5 | $0.00009 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design
Contract
| Field | Bound contract |
|---|---|
| Trigger | Starting UI work, defining palettes or design tokens, correcting AI-generic, vibe-coded, or default-framework design, or persisting an approved design system to DESIGN.md. |
| Authority | Reversible local: writes only local UI direction, token, and implementation artifacts; persist mode also writes DESIGN.md, CLAUDE.md pointers, and preview artifacts. Rollback is version control. No remote mutation. |
| Side effect | Local writes to the picked mode's artifacts only, bounded to the current project directory. |
| Done | Implement mode: one defensible direction is implemented consistently across palette, typography, spacing, density, and motion, and the audit passes clean. Persist mode: an approved design system is persisted in DESIGN.md. |
Inputs
- Mode:
implement(direction and token implementation) orpersist(propose, preview, and persist an approved system to DESIGN.md). Required; defaultimplementwhen unstated. - The surface being designed (landing, dashboard, settings, docs, one-screen tool, TUI, CLI, desktop app). Required.
- The runtime or framework in use (vanilla CSS/HTML, React/Tailwind/shadcn, Bubble Tea/Ratatui/Textual, clap/cobra/cmdliner/typer, Tauri/Slint/egui/Iced, Qt/QML). Required before step 6 in implement mode.
- Primary user and density target. Required for framing; state assumptions if not supplied.
- Existing project context (PRD, brand brief, design tokens, component library, an existing DESIGN.md to extend). Optional; load when present.
- Persist mode only: user approval is the in-loop gate. No design system is persisted until the user approves it.
Procedure
Direction precedes tokens; tokens precede code. The picked direction is the contract. Restraint is the default; reach for decoration only when a named surface goal demands it. Balance, not maximalism, not minimalism.
- Frame the surface. Identify register first: brand (marketing, landing, campaign, long-form, portfolio; design IS the product) or product (app UI, admin, dashboard, tool; design SERVES the product). Detection rule, first match wins: (a) cue in the task ("landing page" / "campaign hero" → brand; "dashboard" / "settings panel" → product); (b) surface in focus or route segment (
/marketing/*vs/app/*); (c) register field in project context. Then capture surface, primary user, density target, and motion budget in ms. Write one sentence of physical scene (who, where, ambient light, mood) that forces the dark/light decision; category names alone do not force the answer. Mode persist: read any existing DESIGN.md, tokens, and brand guidance first; name missing context rather than inventing it. Done when: register is named, the four framing fields are captured, and the dark/light sentence is written.
What ships with it
21 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.
- agents/openai.yaml 209 B
- references/anti-slop.md 14 KB
- references/chinese.md 15 KB
- references/cjk.md 7.8 KB
- references/cli.md 7.7 KB
- references/cognitive-load.md 5.0 KB
- references/design-systems.md 21 KB
- references/desktop.md 11 KB
- references/diversity.md 13 KB
- references/interaction-design.md 8.1 KB
- references/japanese.md 17 KB
- references/korean.md 9.9 KB
- references/motion.md 13 KB
- references/paradigms.md 16 KB
- references/personas.md 7.3 KB
- references/qt.md 6.4 KB
- references/react.md 15 KB
- references/soul.md 13 KB
- references/tui.md 12 KB
- references/ux-writing.md 4.8 KB
- references/web.md 22 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.
- yesterday Changed · -19 lines · +16 tokens per session 8f4532f001f7
- 8d ago First seen · 107 lines · 30 tokens per session scan A 1a12aee762dd
design is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 2,402 once invoked, about $0.0002 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 2026-08-30.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…