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 instructions/uipath/skills/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.svg" alt="Measured on agentmods" 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 | $0.01743 | $0.01743 |
| Opus 5 | $0.00872 | $0.00872 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00174 | $0.00174 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 67 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. - Twin hook scripts — keep in sync. Every session hook exists twice:
hooks/<name>.sh(bash — macOS, Linux, Windows with Git Bash) andhooks/<name>.ps1(PowerShell 5.1/7+ — Windows without Git Bash). The two files are behavioral twins: any change to one REQUIRES the equivalent change to the other in the same PR.hooks/hooks.jsonregisters a single bash/PowerShell polyglot command per event that dispatches to the twin matching the executing shell — do not add ashellfield to these entries; the polyglot depends on Claude Code's default shell selection.
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 Changed · +10 lines · +322 tokens per session 56deef2c53cb
- 6d 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 (154 stars, last pushed today), licensed MIT. It adds 1,743 tokens to every session, about $0.0087 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.