power-automate-solutions

power-automate-solutions is a skill for Claude Code, Codex from Wals-pro/claude-power-automate. It costs 78 tokens per session (932 once invoked), scanned A, original, MIT.

A command-line workflow for managing Microsoft Power Platform solutions and environment variables. Solutions package flows and related components for deployment, while environment variables hold values that differ between environments such as development and production.

In plain words
What is it for?
Use it to list and inspect solutions, manage solution components, read or set typed environment-variable values, handle Azure Key Vault secrets, and support development-to-production deployment.
Why use it?
It helps keep editable work in development and deploy the packaged result through environments without hard-coding environment-specific values. It also provides safer handling for secret values.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to list and inspect solutions, manage solution components, read or set typed environment-variable values, handle Azure Key Vault secrets, and support development-to-production deployment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wals-pro/claude-power-automate/power-automate-solutions
Install

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.

Any agent
npx skills add Wals-pro/claude-power-automate --skill power-automate-solutions
Clone the repo
git clone --depth 1 https://github.com/Wals-pro/claude-power-automate

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for power-automate-solutions

README.md
[![agentmods](https://agentmods.dev/badge/skills/wals-pro/claude-power-automate/power-automate-solutions/github.svg)](https://agentmods.dev/skills/wals-pro/claude-power-automate/power-automate-solutions)
Your own site
<a href="https://agentmods.dev/skills/wals-pro/claude-power-automate/power-automate-solutions"><img src="https://agentmods.dev/badge/skills/wals-pro/claude-power-automate/power-automate-solutions/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.

agentmods 80×15 button for power-automate-solutions

Your own site · 80×15
<a href="https://agentmods.dev/skills/wals-pro/claude-power-automate/power-automate-solutions"><img src="https://agentmods.dev/badge/skills/wals-pro/claude-power-automate/power-automate-solutions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00932
Opus 5 $0.00039 $0.00466
Sonnet 5 $0.00016 $0.00186
Haiku 4.5 $0.00008 $0.00093

Measured 12d ago against content hash 694120a3d783, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

power-automate-solutions 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 12d 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.

skills/power-automate-solutions/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power Automate Solutions & Environment Variables

Use this skill for application lifecycle management (ALM) of Power Platform cloud flows: solutions, environment variables, and the DEV -> PROD pipeline. The default tool is the power-automate CLI.

Core idea

  • Solutions are the unit of deployment. Unmanaged solutions hold the editable source in DEV; managed solutions are the deployed result in PROD.
  • Environment variables parameterize a solution so the same flow behaves correctly across environments (e.g. a different API base URL or record id in DEV vs PROD). A variable has a definition (schema name, type, optional default) and, per environment, a value.
  • Create/edit flows in DEV inside an unmanaged solution, then ship the solution through the pipeline. Never edit on PROD directly.

Commands

# Solutions
power-automate solutions --profile acme                 # list (managed + unmanaged)
power-automate solutions --profile acme --unmanaged-only
power-automate solution-components --profile acme --solution <unique-name>

# Environment variables
power-automate env-vars --profile acme                  # all definitions + current/default values
power-automate env-vars --profile acme --solution <unique-name>   # only this solution's variables
power-automate env-var-get --profile acme acme_ApiBaseUrl
power-automate env-var-set --profile acme acme_ApiBaseUrl "https://api.example.com" --solution <unique-name> --dry-run
power-automate env-var-set --profile acme acme_ApiBaseUrl "https://api.example.com" --solution <unique-name>

Add a new flow to a solution at creation time so it ships through the pipeline:

power-automate create --profile acme flow.json --name "My Flow" --solution <unique-name> --dry-run

Secret-handling rules (read before touching values)

  • Secret-type environment variables are backed by Azure Key Vault. The CLI masks their values by default (<secret · Azure Key Vault-backed>). --reveal-secret shows only the Key Vault reference, never the secret value itself.
  • env-var-set refuses Secret-type variables. Configure those in the Power Platform portal or via a Key Vault reference — never pass a secret as a CLI argument (it would land in shell history, logs, and Dataverse as plaintext).
  • Never commit real environment variable values, schema names tied to a real customer, or GUIDs into source control. Use placeholders.

Read the full file on GitHub · 85 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 85 lines · 78 tokens per session scan A 694120a3d783

Subscribe to this mod's changes

power-automate-solutions is a skill published in the GitHub repository Wals-pro/claude-power-automate (11 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 932 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 2026-08-31.