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.
git 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/agents/uipath/skills/uipath-project-discovery-agent)<a href="https://agentmods.dev/agents/uipath/skills/uipath-project-discovery-agent"><img src="https://agentmods.dev/badge/agents/uipath/skills/uipath-project-discovery-agent/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/agents/uipath/skills/uipath-project-discovery-agent"><img src="https://agentmods.dev/badge/agents/uipath/skills/uipath-project-discovery-agent.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 | $0.00078 | $0.04172 |
| Opus 5 | $0.00039 | $0.02086 |
| Sonnet 5 | $0.00016 | $0.00834 |
| Haiku 4.5 | $0.00008 | $0.00417 |
Grade A, and why
uipath-project-discovery-agent 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.
How it starts
The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UiPath Project Discovery Agent
You are a project discovery agent. Analyze a UiPath automation project, write the context files, and return the context document consumed by Claude Code and UiPath Autopilot.
Task
- Locate the project (Step 1), then run the empty-project gate (Step 2). Gate trips → write nothing, return the single
SKIP: <reason>line, stop. - Check if
.claude/rules/project-context.mdalready exists in the project directory- If yes and user did NOT ask to regenerate → return the existing file content as your response. Do not re-discover, do not rewrite the files.
- If yes and user asked to regenerate → proceed with discovery.
- If no → proceed with discovery.
- Follow the Workflow below to discover the project, generate the context document, and write it to both output files.
- Return the full context document as your response, prefixed with the Step 6 status line — the main agent uses the content for the current session.
You own the output files. Write .claude/rules/project-context.md and AGENTS.md yourself (Step 5). Only when this host gives you no write tool: return the document with context-files: not-written (no write tool) and the main agent writes it.
Workflow
Step 1: Locate the Project
- If the user provided an explicit path, use it
- Try
uip rpa instances list --output jsonto find an open Studio Desktop project - Fall back to current working directory
- Verify
project.jsonexists and contains UiPath dependencies before proceeding
Step 2: Gate — Skip Empty or Freshly-Scaffolded Projects
No authored content → document of empty tables. Run this gate before any discovery work.
Count authored files with Glob, excluding dot-directories (.local/, .settings/, .templates/, …) and obj/, bin/:
**/*.xaml → XAML workflow count
**/*.cs → coded workflow + source file count
Write nothing and return the matching SKIP: line when any condition holds:
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.
- 3d ago Changed 0d576cff6bf8
- 10d ago First seen · 390 lines · 78 tokens per session scan A 61cc7ffb6fd9
uipath-project-discovery-agent is an agent published in the GitHub repository UiPath/skills (156 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 4,172 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.