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 rules/originaleric/dig-ui-skill/dig-uigit clone --depth 1 https://github.com/originaleric/dig-ui-skillWhat 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 | $0.00030 | $0.00337 |
| Opus 5 | $0.00015 | $0.00169 |
| Sonnet 5 | $0.00006 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
dig-ui 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 2d 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.
What it actually says
Use the Dig UI skill installed at {{SKILL_DIR}}.
Start from SKILL.md, then load only the references you need:
- Always read
references/global-rules.mdas the canonical English rules. If the user works in Chinese or asks for Chinese context, also readreferences/global-rules.zh-CN.md. Then readreferences/global-rules.local.mdwhen present unless the user explicitly says no global rules. - When the user asks to add, update, remove, or refine personal UI preferences, read
references/local-rules-builder.mdand update the user local rules source of truth instead of editing shared global rules. - Choose one catalog from
references/catalogs/before writing styles. - Use brand catalogs for named brands/products/visual languages; use palette catalogs for mood, overall site palette, or color-composition requests.
- Choose a layout recipe from
references/layouts/when structuring pages. - Use
references/tokens.md,references/primitives.md, andreferences/checklist.mdas needed.
When implementing or reviewing UI:
- Default to the
digcatalog unless the page clearly needs another catalog such aswiseorapple. - Layout defines structure; catalog defines visual language. Do not mix multiple catalogs on one page.
- Prefer tokenized CSS variables over hard-coded colors, radii, and shadows.
- Avoid generic purple SaaS gradients and noisy neon palettes.
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.
- 2d ago First seen · 24 lines · 30 tokens per session scan A a6053e35413d
dig-ui is a cursor rule published in the GitHub repository originaleric/dig-ui-skill (229 stars, last pushed 13d ago), licensed Apache-2.0. It adds 30 tokens to every session and 337 once invoked, about $0.0002 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.