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.
git clone --depth 1 https://github.com/giselles-ai/giselleWrote 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/rules/giselles-ai/giselle/design-mode)<a href="https://agentmods.dev/rules/giselles-ai/giselle/design-mode"><img src="https://agentmods.dev/badge/rules/giselles-ai/giselle/design-mode/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/rules/giselles-ai/giselle/design-mode"><img src="https://agentmods.dev/badge/rules/giselles-ai/giselle/design-mode.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 | $0.00017 | $0.01052 |
| Opus 5 | $0.00009 | $0.00526 |
| Sonnet 5 | $0.00003 | $0.00210 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
design-mode 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- design-mode — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Mode
Design Mode is intended for users who excel in design rather than software development. It enables direct application design by editing Next.js code instead of using tools like Figma.
- Avoid destructive changes.
- Limit modifications to appearance or behavior only.
- If functional changes or additions are necessary, create a consultation text for engineers and encourage the user to seek their input.
How to Start Design Mode
The step-by-step procedure below MUST be followed in order. Each step MUST be completed before proceeding to the next one. No steps should be skipped.
1. Check Requirements
All required tools must be verified in the following order:
-
Node.js Version Check
node -v✅ REQUIRED: Version must be 22.14.0 or later ❌ If version requirement not met: See
./nodejs.mdcfor installation instructions -
pnpm Version Check
pnpm -v✅ REQUIRED: Version must be 10.2.1 or later ❌ If version requirement not met: See
./nodejs.mdcfor installation instructions -
Vercel CLI Version Check
vercel --version✅ REQUIRED: Version must be 41.6.0 or later ❌ If Vercel CLI is missing: Install with the command below
pnpm add -g vercel -
Vercel CLI Login Status
vercel whoami✅ REQUIRED: Must show a username ❌ If not logged in: See
./vercel-cli.mdcfor login instructions -
Vercel Project Link Check
[ -f .vercel/project.json ] && echo "Project is linked" || echo "We need to link vercel project"✅ REQUIRED: Must show "Project is linked" ❌ If "We need to link vercel project" is displayed: a. List available teams:
bash vercel team listb. Switch to team and list projects:bash vercel team switch [team-name] vercel project listc. Link the project:bash vercel link --yes --project [project-name]
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.
- 10d ago First seen · 150 lines · 17 tokens per session scan A 5f9bf41b449c
design-mode is a cursor rule published in the GitHub repository giselles-ai/giselle (555 stars, last pushed 8d ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,052 once invoked, about $0.0001 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 cursor rules, from other repositories
ui-components
This file outlines rules for using shadcn/ui components within the AgentDock OSS Client application.
design
All tasks related to updating frontend components, CSS, and general styling.
codex-premium-website-skills
Apply Codex Skills standards to frontend, website, motion, accessibility, QA, agent reasoning, and handoff work.
color-tokens
A rule set for choosing interface colors through shared semantic design tokens. These tokens are named meanings such as primary, success, notice, or destructive rather than fixed color values.
figma-to-code
Rules for converting a Figma interface design into code, covering design analysis, component splitting, and style implementation. Figma is a tool for creating and sharing interface designs.
desktop-layout
A set of desktop web-page layout rules covering content widths, spacing, text sizes, corner rounding, buttons, icons, and narrow-screen behaviour.