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 skills add jnPiyush/AgentX --skill power-automate-desktopgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/skills/jnpiyush/agentx/power-automate-desktop)<a href="https://agentmods.dev/skills/jnpiyush/agentx/power-automate-desktop"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/power-automate-desktop/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/skills/jnpiyush/agentx/power-automate-desktop"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/power-automate-desktop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00899 |
| Opus 5.5 | $0.00030 | $0.00360 |
| Sonnet 5.5 | $0.00015 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
power-automate-desktop 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 1mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power Automate Desktop (RPA)
Purpose: design Power Automate desktop flows that automate UI-driven work no API exposes -- the automation of last resort -- with robust selectors, variables, and error handling.
When to Use (RPA Is a Last Resort)
Use a desktop flow only when there is no connector, API, or cloud flow that can do the job:
- Driving a legacy desktop app or a website with no API
- Screen-scraping or form-filling a system you cannot change
Always prefer, in order: native connector -> custom connector over a documented API -> HTTP action -> desktop flow (RPA). RPA is brittle (UI changes break selectors) and needs a machine/runtime -- only choose it when nothing higher wins.
Attended vs Unattended
| Attended | Unattended | |
|---|---|---|
| Runs | With a signed-in user watching | On a machine with no interactive user |
| Trigger | User starts it, or a cloud flow | Scheduled / cloud-flow, queued on a machine group |
| Use for | Human-in-the-loop, desktop apps the user owns | Lights-out batch processing |
Flow Structure (Designer Model)
A desktop flow is an ordered list of actions grouped into optional subflows, operating on variables.
Main (subflow)
1. Set variable NewVar = %FormInput%
2. Launch browser (or Run application)
3. Populate text field on window (UI element selector)
4. Click UI element
5. If <condition> ... Else ... End
6. Loop / For each %item% in %list%
7. On block error -> retry / continue / go to label
- UI elements / selectors: captured per target window/control; the most fragile part. Prefer stable attributes (id, name, accessible role) over screen coordinates and ordinal indexes.
- Variables:
%VarName%syntax; typed at runtime (text, number, list, datatable, custom object). - Excel / file / data actions: first-class actions for spreadsheets, CSV, folders -- prefer these over UI automation of Office where possible.
Error Handling
- Wrap fragile UI actions in On block error with retry counts and a fallback path.
- Set per-action timeouts; do not let a missing window hang the run.
- Capture a screenshot + log on failure for unattended diagnosis.
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.
- 1mo ago Changed 3d9c1c6ba549
- 1mo ago First seen · 73 lines · 74 tokens per session scan A 7c88a527e4cc
power-automate-desktop is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 74 tokens to every session and 899 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
cli-anything-macrocli
Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes macro run and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).
agent-browser
Use the agent-browser CLI to exercise web interfaces, inspect rendered accessibility state, verify interactions, and capture screenshots. Use for browser-based UI testing and evidence collection. Do not use as a substitute for deterministic Playwright coverage when an automated regression test is the requested…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Interceptor
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…