diagnose-flow

diagnose-flow is a skill for Claude Code from microsoft/power-platform-skills. It costs 38 tokens per session (1,118 once invoked), scanned A, original, MIT.

A diagnostic workflow for investigating one failed Power Automate flow run using its environment, flow, and run IDs.

In plain words
What is it for?
Use it to analyze failed or timed-out actions, map dependencies and parallel branches, find the root failure, and suggest remediation.
Why use it?
It gathers the run status, action trace, flow definition, and loop details needed to identify what failed and why.

Skill for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Claude Code.

Part of the power-automate plugin — 9 skills shipped together

Good fit Use it to analyze failed or timed-out actions, map dependencies and parallel branches, find the root failure, and suggest remediation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/power-platform-skills/diagnose-flow
About the project

microsoft/power-platform-skills is a plugin marketplace containing reusable skills, agents, and commands for developing with Microsoft Power Platform. Developers use it to build and deploy Power Pages sites, model-driven Power Apps, and related solutions through Claude Code or GitHub Copilot. The catalogue entries are the marketplace's included skills, agents, plugins, and other agent components.

microsoft/power-platform-skills · 844 stars · on GitHub · aka.ms

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 microsoft/power-platform-skills --skill diagnose-flow
Clone the repo
git clone --depth 1 https://github.com/microsoft/power-platform-skills

Made for: Claude Code.

Or install power-automate, the plugin that ships this one along with the rest of its 9 skills.

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 diagnose-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/power-platform-skills/diagnose-flow.svg)](https://agentmods.dev/skills/microsoft/power-platform-skills/diagnose-flow)
Your own site
<a href="https://agentmods.dev/skills/microsoft/power-platform-skills/diagnose-flow"><img src="https://agentmods.dev/badge/skills/microsoft/power-platform-skills/diagnose-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,118 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 8
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00038 $0.01118
Opus 5 $0.00019 $0.00559
Sonnet 5 $0.00008 $0.00224
Haiku 4.5 $0.00004 $0.00112

Measured 4d ago against content hash 59874982a85c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

diagnose-flow 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 4d 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.

plugins/power-automate/skills/diagnose-flow/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Flow Diagnostic Agent

You are an autonomous diagnostic agent. Given environment, flow, and run IDs, perform a comprehensive failure analysis.

Input

Parse $ARGUMENTS for: environment ID, flow ID, run ID.

Tools

This skill uses the FlowAgent MCP tools, referred to by bare name (clients surface them as mcp__flowagent__<tool> in Claude Code or flowagent-<tool> in Copilot CLI). If no MCP tools are present, the plugin is not wired up — run the setup skill.

Workflow

  1. Triage with diagnose_run, then gather full context in parallel:

    • diagnose_run — classified failed/timed-out actions with a remediation each (start here)
    • get_run_details for overall run status
    • get_run_actions for the full action-level execution trace
    • get_flow for definition context
    • For a failed loop, get_run_action_repetitions on an action inside the loop (the container returns none) to find the failing iteration
  2. Build execution graph: Map each action's runAfter dependencies. Identify parallel branches.

  3. Identify failed actions: Filter for status != Succeeded. Classify each as:

    • Root failure: dependencies all Succeeded but this action failed
    • Cascading skip: skipped because a dependency failed
  4. Analyze each root failure against common patterns:

    • Authorization/Connection errors
    • Expression evaluation failures
    • HTTP 4xx/5xx from external services
    • Timeout errors
    • Parameter validation failures (empty required fields, wrong enum values)
    • Action type mismatches (OpenApiConnection vs OpenApiConnectionWebhook)
  5. Cross-reference with definition: Check if the action's parameters, connection references, or expressions have issues visible in the definition.

  6. Write diagnosis report with:

    • Execution timeline
    • Root cause identification
    • Specific fix with code changes
    • Confidence level (high/medium/low)
  7. Optionally generate fixed definition: If the fix is a definition change, apply it with edit_flow (surgical, one action/parameter) — fall back to update_flow only for large rewrites.

Read the full file on GitHub · 57 lines

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. 4d ago First seen · 57 lines · 38 tokens per session scan A 59874982a85c

Subscribe to this mod's changes

diagnose-flow is a skill published in the GitHub repository microsoft/power-platform-skills (844 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 1,118 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories