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 design-gate-brainstorminggit 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-gate-brainstorming)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/design-gate-brainstorming"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/design-gate-brainstorming/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/design-gate-brainstorming"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/design-gate-brainstorming.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 | $0.00044 | $0.01465 |
| Opus 5 | $0.00022 | $0.00732 |
| Sonnet 5 | $0.00009 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
design-gate-brainstorming 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.
This is a copy
94% identical to design-gate-brainstorming — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design gate brainstorming
Contract
| Field | Bound contract |
|---|---|
| Trigger | User requests creative work (a feature, component, or behavior change) or supplies a raw idea or repository to develop, and no approved design exists; fires before any implementation action on every such path. |
| Authority | Reversible local: writes only named design documents, builder profiles, analytics records, and spec documents depending on path; rollback is undo. No remote mutation. The idea path writes the named design document, builder profile, and analytics records; the architectural path writes only the named spec document; bounded and spike paths write no files. URL opens are reads. |
| Side effect | Idea path: a redaction-checked design document, builder profile, and session analytics records on local disk. Architectural path: a spec document and optionally a spec-reviewer subagent dispatch. Bounded path: an in-chat design only. Spike path: a recommendation only; anything built is labeled throwaway. |
| Done | The user explicitly approved the intent before any implementation. Idea path ends at an approved, saved, redaction-checked design document handed off with a tiered closing and next-skill offer; bounded at in-chat design approval; spike at a reported recommendation; architectural at a self-review-clean spec plus handoff to the plan writer. |
Inputs
- A creative-work request (feature, component, or behavior change), or a raw idea description or repository path to develop. One must be supplied.
- Any already-approved design present in context. Optional; if present, this skill does not route.
- The user, in-loop, to approve or reject the produced design or recommendation. Required on every path.
- Prior context for the idea path. Optional; absent context is gathered from the repository or the idea alone.
Procedure
- On any creative-work request with no approved design already in context, stop implementation and route. Confirm at the trust boundary that the request is creative work and that no approved design exists; if an approved design is present, do not route. Done when: the request is confirmed as creative work with no approved design, or the skill stands down because an approved design exists.
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.
- 4d ago First seen · 61 lines · 44 tokens per session scan A 10c19f0a3da2
design-gate-brainstorming is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,465 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to design-gate-brainstorming, differing in 0 lines, and is treated as a copy.
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…