cursor-rule

cursor-rule is a cursor rule for coding agents from Alexsun1one/paper-operators. It costs 0 tokens per session (455 once invoked), scanned A, original, MIT.

A rule for planning illustrations and writing prompts for articles, explainers, blog posts, and other visual content.

In plain words
What is it for?
Use it to plan article figures, explainer images, concept visuals, and image-generation prompts, including Chinese-language content when appropriate.
Why use it?
It gives image requests a clear subject, reader takeaway, mood, layout, and quality check instead of producing an unfocused visual brief.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/alexsun1one/paper-operators/cursor-rule
Clone the repo
git clone --depth 1 https://github.com/Alexsun1one/paper-operators
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 455 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00455
Opus 5 $0.00000 $0.00228
Sonnet 5 $0.00000 $0.00091
Haiku 4.5 $0.00000 $0.00046

Measured 3d ago against content hash 153cf73b10fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-rule 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 3d 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.

agent-guides/cursor-rule.mdc · 40 lines

What it actually says

Paper Operators

Use this rule when the user asks for article illustrations, blog figures, WeChat article images, explainer visuals, concept images, or image prompts.

Default to Chinese if the user writes Chinese.

Workflow:

  1. Identify the source anchor: the article sentence, paragraph, conflict, turn, claim, or feeling worth visualizing.
  2. State the reader takeaway in one sentence.
  3. Choose the domain and mood.
  4. Decide whether a folded-paper operator is necessary.
  5. Run the inclusion test: what breaks if the operator is removed?
  6. Choose a paper-world scene and core action.
  7. Use readable labels in the user's language.
  8. Produce the final image prompt or plan.
  9. QA for clarity, action, label readability, and style drift.

Visual DNA:

  • 16:9 horizontal article body image by default.
  • High-angle tabletop paper-model scene.
  • Folded-paper people. The face is plain by default, or one simple hand-drawn expression (a few line strokes for brows/eyes and mouth, profile or three-quarter, looking at the work) when it encodes the operator's state (effort, focus, strain, relief, care). Keep it abstract to avoid the uncanny valley; never realistic, never head-on, never Xiaohei white-dot eyes.
  • Tactile paper, labels, trays, frames, gates, paths, shelves, folders, scales, lenses, light cards.
  • Stage relationships as deep 3D paper scenes (material arrangement + line/loop guidance + operator state), not flat paper-textured chart icons.
  • Blue carrier ribbon/path when useful.
  • Short readable labels by default.
  • One sentence strip is allowed when it clarifies the takeaway.

Avoid generic mascots, robots, stick figures, stock infographic icons, PPT charts, Xiaohei-like black figures (black blob body, white-dot eyes), cute grins aimed at the reader, fake tiny text, and blank labels unless the user explicitly wants post-production overlay.

For the full portable guide, reference agent-guides/paper-operators-agent.md.

Changes

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.

  1. 3d ago First seen · 40 lines · 0 tokens per session scan A 153cf73b10fb

Subscribe to this mod's changes

cursor-rule is a cursor rule published in the GitHub repository Alexsun1one/paper-operators (107 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 455 tokens. 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.