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 product-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/product-design)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/product-design"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/product-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/outlinedriven/odin-claude-plugin/product-design"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/product-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01368 |
| Opus 5 | $0.00019 | $0.00684 |
| Sonnet 5 | $0.00008 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
product-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 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product design
Contract
| Field | Bound contract |
|---|---|
| Trigger | product design, what should this do, interface should do, before anyone builds it, product requirements |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Analyzes the user request, existing project files, design system artifacts, and AGENTS.md. |
| Side effect | Chat output only: product decisions, surface definitions, findings, and routed follow-on work. |
| Done | A report is returned defining what the interface does, its surfaces and reachable states, scope and consequence per action, findings with rule IDs, and routed follow-on work; or the report is labeled INCOMPLETE with the blocking gap named. |
Inputs
Required:
- The user's request text.
Required when available:
- The project design system, existing UI, or AGENTS.md.
- The surface or component under design.
- Any existing spec, brief, or mockup.
Procedure
-
Classify the request into one mode. Pick exactly one from the mode table below; when the verb is ambiguous, shape is the default. Modes chain: shape leads into spec; review leads into harden. Done when: one mode is named.
-
Locate authority in this order: (a) the user's explicit goal and constraints, (b) verified user and product evidence, (c) project-canonical guidance in AGENTS.md and the design system, (d) this skill's standards. Load
references/rules.mdplus the mode's other reference files as listed in the mode table; rules.md loads in every mode. Every rule ID cited later must appear in a loaded file. Done when: the authority order is resolved and the mode's references are loaded. -
Write the internal brief (shape, spec, harden) before proposing UI: job, desired outcome, consequence, object, action scope, permissions, as defined in rules.md. If job, desired outcome, or consequence cannot be filled, stop and ask; do not propose UI. For spec and action, name the object, scope, and consequence for each action in scope. For shape, spec, and harden, enumerate every reachable state per surface against the checklist in surfaces.md and mark each reachable or unreachable with a reason. Done when: the brief is complete, per-action scope and consequence are named where required, and the reachable-state checklist is walked where required.
What ships with it
6 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.
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 · 67 lines · 39 tokens per session scan A c17b210b99a7
product-design is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,368 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 2026-09-06.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…