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 Wals-pro/claude-power-automate --skill power-automate-referencegit clone --depth 1 https://github.com/Wals-pro/claude-power-automateWrote 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/wals-pro/claude-power-automate/power-automate-reference)<a href="https://agentmods.dev/skills/wals-pro/claude-power-automate/power-automate-reference"><img src="https://agentmods.dev/badge/skills/wals-pro/claude-power-automate/power-automate-reference/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/wals-pro/claude-power-automate/power-automate-reference"><img src="https://agentmods.dev/badge/skills/wals-pro/claude-power-automate/power-automate-reference.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 | $0.00087 | $0.00594 |
| Opus 5 | $0.00044 | $0.00297 |
| Sonnet 5 | $0.00017 | $0.00119 |
| Haiku 4.5 | $0.00009 | $0.00059 |
Grade A, and why
power-automate-reference 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 11d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power Automate Reference
Look here before writing or reviewing a cloud-flow expression or action JSON. This skill ships the canonical Microsoft references inline so you verify names against the real namespace instead of recalling them from training data (which goes stale as Microsoft changes the platform).
Hard rules
- The function namespace is closed. If a name is not in
references/expression-functions.md, it does not exist — do not invent or guess a function. Pick a real one or compose existing ones. - Cloud flows use Workflow Definition Language (WDL) only. Never use Power Fx
functions inside cloud-flow JSON. Power Fx is for desktop flows and other Power
Platform formula surfaces (see
power-automate-expression-syntax). - Secrets in a workflow definition's
parametersuse thesecurestring/secureobjecttypes (aGETwill not return them); real secrets belong in Azure Key Vault, never as literals in the definition. - Use the
?null-safe operator for optional action/trigger outputs. - Prefer real control actions (
If/Switch/Scope/Foreach/Until) over stackingComposeactions to fake logic.
Procedure
- Classify what you need:
- a function (name / category / does it exist) →
references/expression-functions.md - a trigger or action (
typevalue, runAfter) →references/triggers-and-actions.md - the definition shape, parameter types, or operators →
references/workflow-definition-language-schema.md
- a function (name / category / does it exist) →
- Read the matching reference file and use the exact names/types it lists.
- Only open the canonical Microsoft Learn link (in each file) when you need the newest behavior or an edge detail the reference does not cover.
Related skills
power-automate-expression-syntax— how to compose and validate expressions (this skill is the lookup of what exists).power-automate-action-configuration— connector/action payload shapes.power-automate-docs— router to the wider Microsoft Learn documentation.power-automate-workflow-patterns— flow architecture (and avoiding Compose sprawl).
What ships with it
3 files 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.
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.
- 11d ago First seen · 53 lines · 87 tokens per session scan A 89f4d54ef951
power-automate-reference is a skill published in the GitHub repository Wals-pro/claude-power-automate (11 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 594 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.
Other skills, from other repositories
azure-cli
Use the Azure CLI to manage subscriptions, resource groups, AKS, App Service, Key Vault, and role assignments.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.