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/uipath/skills/skill-structuregit clone --depth 1 https://github.com/UiPath/skillsWhat 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 | $0.00000 | $0.00434 |
| Opus 5 | $0.00000 | $0.00217 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
skill-structure 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
Every skill under skills/uipath-<kebab-case>/ must have a SKILL.md with valid YAML frontmatter: name (matching folder name exactly) and description (under 1024 characters — repo cap; Claude Code's hard truncation for description + when_to_use is 1,536 chars).
The description must front-load skill identity and unique file/domain signals (e.g. .cs, .xaml, .flow, servo) within the first ~100 characters. Use compact → redirects for commonly confused sibling skills (e.g. For XAML→uipath-rpa). Start with [PREVIEW] for unstable skills. Do NOT use verbose TRIGGER when: / DO NOT TRIGGER when: clauses or nest fields under metadata: — both cause Claude Code to drop the field.
SKILL.md body order: Title → When to Use → Critical Rules (numbered) → Workflow/Quick Start → Reference Navigation → Anti-patterns. Reference files use kebab-case; guides end with -guide.md; templates end with -template.md or -template.<ext>. Skills must be self-contained — no cross-skill references.
Full reference: .claude/rules/skill-structure.md.
Before changing flavor markers, sparse overrides, generic discovery,
package construction, publishing, or flavor CI, read
.claude/skills/manage-skill-flavors/SKILL.md completely and follow its
reference-routing instructions.
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 · 18 lines · 0 tokens per session scan A 25dfc3f9156f
skill-structure is a cursor rule published in the GitHub repository UiPath/skills (150 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 434 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.
Other cursor rules, from other repositories
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
moyu
当检测到过度工程模式时自动激活：修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.
selectools-providers
Rules for working with LLM provider adapters in selectools.
cursorrules
AgentAnycast is a decentralized P2P runtime for the A2A (Agent-to-Agent) protocol.