Borrowing it
Nothing to install: this file belongs to UiPath/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/UiPath/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/UiPath/skillsWrote 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/instructions/uipath/skills/claude-md)<a href="https://agentmods.dev/instructions/uipath/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/uipath/skills/claude-md/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/instructions/uipath/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/uipath/skills/claude-md.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 | $0.02261 | $0.02261 |
| Opus 5.5 | $0.00904 | $0.00904 |
| Sonnet 5.5 | $0.00452 | $0.00452 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade A, and why
skills CLAUDE.md 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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UiPath Agent Skills — Project Rules
This repository contains self-contained AI agent skills for UiPath automation development. Skills are installed as a Claude Code plugin and teach AI agents how to build, run, test, and deploy UiPath automations.
Architecture
- Skills are self-contained. Each skill under
skills/must function on its own: it MUST NOT import, inline, or read another skill's files, and MUST still deliver its core value if sibling skills are absent. A skill MAY delegate a task to a sibling skill in this same plugin at runtime (e.g., spawn a subagent that hands an artifact edit to the artifact's owning domain skill) when that work is the sibling's domain — provided the delegation degrades gracefully (the skill still presents an actionable result when the sibling is unavailable). - SKILL.md is the canonical default contract. Every skill folder must have a complete
SKILL.mdwith valid YAML frontmatter. Local/default consumers can understand it without a flavor manifest or runtime resolver. Shared guidance stays there; only genuinely different passages may be enclosed by named flavor-block comments. - Custom flavors inherit the complete catalog and contain only sparse exceptions. Every flavor ships every canonical skill. Files under
skill-flavors/<flavor>/<skill>/mirror canonical skill paths and contain only complete replacement blocks. If no override exists, the canonical file is intentionally reused unchanged. Do not duplicate a whole skill merely to change a few paragraphs. - Build files before packages. Build complete
defaultand custom-flavor skill trees, validate those final files, and only then stage packages. Consumers must copy a finished tree; they must not interpret flavor markers or compose Markdown at runtime. - Session hooks are Node scripts or direct
uipingestion — never shell scripts. Telemetry ships NO script:hooks/hooks.jsonpipes the raw hook payload touip track --hook, and the field derivation lives in the CLI (UiPath/clitrack-hook.ts, guarded by its vitest suite). The remaining session hooks are each onehooks/<name>.mjsrun bynode. Bothnodeanduipare native-executable entry points, so no shell dialect and no PowerShell execution policy applies, and both are present wherever the skills were installed through the Node-baseduipCLI. Eachhooks.jsonentry is a bash/PowerShell polyglot command whose both branches guard for the missing binary (silent exit 0) — telemetry's PowerShell branch resolvesuip.cmdexplicitly, never the bareuip(PowerShell would prefer npm'suip.ps1shim, which execution policy can block). Do not add ashellfield to these entries; the polyglot depends on Claude Code's default shell selection. Do NOT reintroduce.sh/.ps1hook implementations: the retired PowerShell twins required an Authenticode signing gate at publish and still failed under Group-Policy execution policy.
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.
- 8d ago Changed · +1 lines · +57 tokens per session cdc176a668f5
- 1mo ago Changed · +150 tokens per session 2605503cfc24
- 1mo ago Changed · +8 lines · +311 tokens per session 52026901f729
- 2mo ago Changed · +10 lines · +322 tokens per session 56deef2c53cb
- 2mo ago First seen · 57 lines · 1,421 tokens per session scan A 5bbd32d39a6f
skills CLAUDE.md is an instructions file published in the GitHub repository UiPath/skills (177 stars, last pushed yesterday), licensed MIT. It adds 2,261 tokens to every session, about $0.0090 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 2026-08-30.
skills CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills CLAUDE.mdUiPath/skills | Instructions file | 177 | yesterday | MIT | A | 2,261 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |