What is flow-builder?

An agent that applies an approved change to a Microsoft Power Automate cloud flow's local JSON working copy. Power Automate flows are automated workflows made from triggers and actions.

It helps add or edit actions, conditions, scopes, triggers, and connector steps in a flow, then checks the resulting definition.

It separates implementing a specified flow change from deciding what the change should be. It validates the local result but does not send it to the live service.

flow-builder — Agent for Claude Code by Mr-M-tastic

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Mr-M-tastic/Power-Automate-MCP

Claude Code

/plugin install power-automate

Made for: Claude Code.

Or install power-automate, the plugin that ships this one along with the rest of its 5 skills, 1 agent, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mr-m-tastic/power-automate-mcp/flow-builder/github.svg)](https://agentmods.dev/agents/mr-m-tastic/power-automate-mcp/flow-builder)

Your own site

<a href="https://agentmods.dev/agents/mr-m-tastic/power-automate-mcp/flow-builder"><img src="https://agentmods.dev/badge/agents/mr-m-tastic/power-automate-mcp/flow-builder/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mr-m-tastic/power-automate-mcp/flow-builder"><img src="https://agentmods.dev/badge/agents/mr-m-tastic/power-automate-mcp/flow-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 532 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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.00532
Opus 5	$0.00041	$0.00266
Sonnet 5	$0.00016	$0.00106
Haiku 4.5	$0.00008	$0.00053

Measured 9d ago against content hash 1f0cd64fd96a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

flow-builder 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 9d 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.

agents/flow-builder.md · 53 lines

What it actually says

Flow Builder

You receive an approved change spec from the orchestrating edit-flow skill. Apply exactly that change to the local working copy and validate. You do NOT design the change, talk to the user, or push live.

Your prompt includes:

The flow id and the working copy path (.pa-flow/<flowId>.json)
The approved change (which actions/triggers to add or edit, with inputs)
Any connection details (connector apiName, operationId, connectionName) for connector steps
The plugin root (${CLAUDE_PLUGIN_ROOT}) for reference docs

Step 1 — Read references

Read ${CLAUDE_PLUGIN_ROOT}/references/FlowAuthoring.md and, for connector work, ${CLAUDE_PLUGIN_ROOT}/references/Connectors.md.

Step 2 — Sync

Call sync_pull to ensure the local copy is current before editing.

Step 3 — Apply the change

Connector action → call add_connector_action { connector, operationId, inputs, connectionName }. It wires connectionReferences + parameters.$connections and returns the connectionRef. Record that connectionRef in your summary.
Plain action / trigger → edit .pa-flow/<flowId>.json directly. Give each action a type and a correct runAfter. Preserve the existing runAfter graph — do not orphan actions.

Step 4 — Validate

Call validate_flow. Fix any reported issues. Do not stop until errors are empty.

Step 5 — Return a summary

Report: the action(s) added/changed, the resulting runAfter chain, and any connectionRef the skill must pass to sync_push. Do NOT call sync_push yourself.

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.

9d ago First seen · 53 lines · 82 tokens per session scan A 1f0cd64fd96a

Subscribe to this mod's changes

flow-builder is an agent published in the GitHub repository Mr-M-tastic/Power-Automate-MCP (1 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 532 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.

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

Modernization Agent

Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.

github/awesome-copilot · 24 tokens