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 instructions/the-utopia-studio/skills/agents-mdgit clone --depth 1 https://github.com/The-Utopia-Studio/skillsWrote 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/instructions/the-utopia-studio/skills/agents-md)<a href="https://agentmods.dev/instructions/the-utopia-studio/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/the-utopia-studio/skills/agents-md.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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
skills AGENTS.md 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ceramic Design System agent rules
- Run
npm run ceramic -- manifest --jsonbefore generating UI. - Run
npm run ceramic -- search <intent> --json, then inspect the selected component or template. - Prefer
@utopia-studio-design/design-systemexports over raw shadcn/ui source. - Components consume semantic tokens only. The active theme is
utopia-default. - Request semantic motion only; inspect
npm run ceramic -- motion ceremonial --jsonbefore choosing an application runtime adapter. - Read
npm run ceramic -- docs arabic-friendly --densebefore Arabic or RTL work. - Never invent component props, import paths, tokens, Arabic product copy, or left/right-only APIs.
- Validate with
npm run ceramic:doctorbefore handoff.
Learned User Preferences
- Organize the marketplace into four modules only: GTM, Product, Investments, and Founder Productivity (overflow for skills that do not fit the first three).
- Prefer selective skill imports over bulk-adding external libraries; curate high-judgment additions and skip thin or vendor-locked long-tail skills.
- Keep install UX extremely simple: clear docs plus a copy-paste Claude Code / agent prompt.
- For public web surfaces, use the Utopia Ceramic design system with the
utopia-defaulttheme (including GitHub Pages). - Commit and push only when explicitly asked; stage coherent marketplace slices and avoid scooping unrelated WIP.
Learned Workspace Facts
- This workspace is the Utopia Skills marketplace repo:
https://github.com/The-Utopia-Studio/skillsat/Users/kp/Documents/Utopia Skills. - Canonical skill sources live under
skills/<module>/where module isgtm,product,investments, orfounder-productivity. GTM skills nest one level deeper:skills/gtm/<01–07 submodule>/<skill>/. - Installable packs are
utopia-gtm,utopia-product,utopia-investments, andutopia-founder-productivity(rebuilt intoplugins/); the old cobuild/M1–M9 pack layout is retired. - GTM plugin path is
plugins/utopia-gtm(notplugins/utopia-studio-cobuild-gtm). - Swan GTM P0 skills were adapted into
skills/gtm/(account tiering, warm intros, signal-anchored messaging, deliverability, cold offers, call scorecards, deal velocity, forecasting, outreach execution, earned autonomy). - Public marketing site is GitHub Pages from
docs/with vendoredutopia-defaulttheme assets, live athttps://the-utopia-studio.github.io/skills/. - Ceramic/agent config for this repo includes
.ceramic/, design-system npm packages, and mirrored Ceramic rules inAGENTS.md/CLAUDE.md.
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 · 29 lines · 612 tokens per session scan A b6804485e03e
skills AGENTS.md is an instructions file published in the GitHub repository The-Utopia-Studio/skills (4 stars, last pushed 9d ago), licensed Apache-2.0. It adds 612 tokens to every session, about $0.0031 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 instructions, from other repositories
todo-for-ai AGENTS.md
AGENTS.md instructions for todo-for-ai/todo-for-ai: These constraints are mandatory for all pages and components in this repository.
melta-ui AGENTS.md
Instructions for tsubotax/melta-ui, covering melta ui — ai エージェント作業ガイド, アーキテクチャ概要, 最初に読むファイル, 読み込みモード and 作業ルール.
figma-ios-codegen AGENTS.md
Instructions for mythkiven/figma-ios-codegen, covering project agent rules, 必读规则文件, 何时启用本流程, 铁律（最高优先级） and 架构（1 → 2 → 4；阶段 3 仓外）.
tech-route-maker GEMINI.md
Instructions for Stephen-studying/tech-route-maker: Use SKILL.md as the primary instruction file for tech-route-maker.
industrial-design-portfolio-skill CLAUDE.md
Instructions for truman-t3/industrial-design-portfolio-skill, covering industrial design portfolio (claude code adapter), industrial design portfolio, cross-agent runtime contract, operating contract and select the task mode.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).