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/eagonmeng/sync-blankWrote 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/eagonmeng/sync-blank/concept-design)<a href="https://agentmods.dev/rules/eagonmeng/sync-blank/concept-design"><img src="https://agentmods.dev/badge/rules/eagonmeng/sync-blank/concept-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/rules/eagonmeng/sync-blank/concept-design"><img src="https://agentmods.dev/badge/rules/eagonmeng/sync-blank/concept-design.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 | $0.03024 | $0.03024 |
| Opus 5.5 | $0.01210 | $0.01210 |
| Sonnet 5.5 | $0.00605 | $0.00605 |
| Haiku 4.5 | $0.00302 | $0.00302 |
Grade A, and why
concept-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 1mo 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Applications with Concept Design
This repository is an application meant to be built according to the principles of concept design, a new approach to modularity first introduced in Daniel Jackson's "The Essence of Software". This approach describes a way to build software in terms of concepts, which describe behavior that captures a familiar unit of functionality with a single purpose. These are then composed together using synchronizations, which are declarative statements that describe how actions of different concepts are composed.
Concepts
A concept is a highly-reusable and standalone service designed to fulfill a
single purpose. Unlike microservices or traditional OOP classes, concepts
must remain independent from one another and cannot import or reference
other concepts. They can be specified using a simple specification language and
stored as .concept files, such as:
<concept_spec>
concept User
purpose
to associate identifying information with individuals
state
a set of Users with
a name String
an email String
actions
register (user: Users, name: String, email: String) : (user: Users)
associate user with users
associate name and email if both unique and valid
return the user reference
register (user: Users, name: String, email: String) : (error: String)
if either name or email is invalid or not unique, describe error
return the error description
update (user: Users, name: String) : (user: Users)
if name is unique, update user's name
return the user reference
update (user: Users, name: String) : (error: String)
if name is not-unique, describe error
return the error description
update (user: Users, email: String) : (user: Users)
if email is unique and valid, update id's email
return the user reference
update (user: Users, email: String) : (error: String)
if email is not-unique or invalid, describe error
return the error description
operational principle
after register () : (user: x) and update (name: "xavier") : (user: x)
for any user u such that u's name is "xavier", u must be x
</concept_spec>
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.
- 1mo ago First seen · 294 lines · 3,024 tokens per session scan A 8979f6bf77b7
concept-design is a cursor rule published in the GitHub repository eagonmeng/sync-blank (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,024 tokens to every session, about $0.0121 per session on Opus 5.5. 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 cursor rules, from other repositories
explorer-interface-brief
Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…
prototype-previewer
Build interactive prototype reviewers with synced review notes and Figma capture pages.
figma-performance
Handling large documents efficiently in the Plugin API.
ant-design
A set of guidelines for using Ant Design, a collection of ready-made interface components, in React applications. It covers code organization, performance, security, testing, and common mistakes.
7-day-nextjs-web-design-cursor
A seven-day design workflow for web products that will be built in Next.js.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.