azure-functions-update

azure-functions-update is a skill for Claude Code from Azure/azure-functions-skills. It costs 87 tokens per session (3,902 once invoked), scanned A, original, MIT.

A guided migration process for Azure Functions, Microsoft's serverless cloud programs, with a current path from the C# in-process model to the .NET isolated worker model.

In plain words
What is it for?
Use it only when explicitly asked to run this named workflow for the supported Azure Functions migration scenario.
Why use it?
It keeps programming-model changes separate from language-version and hosting-plan changes, reducing the risk of mixing unrelated migrations.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the azure-functions-skills plugin — 16 skills, 1 hook, 1 MCP server shipped together

Good fit Use it only when explicitly asked to run this named workflow for the supported Azure Functions migration scenario.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/azure/azure-functions-skills/azure-functions-update
About the project

Azure Functions Skills is a repository of agent skills, prompts, reusable definitions, MCP configuration, and telemetry hooks that give coding agents context about Azure Functions development and operations. Developers use it for guidance on triggers, bindings, runtimes, deployment, and code checks, while the catalogue contains its agent-facing add-ons.

Azure/azure-functions-skills · 19 stars · on GitHub

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 Azure/azure-functions-skills --skill azure-functions-update
Clone the repo
git clone --depth 1 https://github.com/Azure/azure-functions-skills

Made for: Claude Code.

Or install azure-functions-skills, the plugin that ships this one along with the rest of its 16 skills, 1 hook, 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.

agentmods badge for azure-functions-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/azure/azure-functions-skills/azure-functions-update/github.svg)](https://agentmods.dev/skills/azure/azure-functions-skills/azure-functions-update)
Your own site
<a href="https://agentmods.dev/skills/azure/azure-functions-skills/azure-functions-update"><img src="https://agentmods.dev/badge/skills/azure/azure-functions-skills/azure-functions-update/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 azure-functions-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/azure/azure-functions-skills/azure-functions-update"><img src="https://agentmods.dev/badge/skills/azure/azure-functions-skills/azure-functions-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,902 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 $0.00087 $0.03902
Opus 5.5 $0.00035 $0.01561
Sonnet 5.5 $0.00017 $0.00780
Haiku 4.5 $0.00009 $0.00390

Measured 15d ago against content hash 2959c193ad8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

azure-functions-update 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 15d 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.

.github/plugins/azure-functions-skills/skills/azure-functions-update/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Azure Functions

Draft. Reply in the user's language unless they request another language. This file is the complete common workflow. Load only the selected scenario for its official sources, extra prerequisites, migration details, and definition of done.

Selection and scope

Start or resume only when the user explicitly names azure-functions-update and asks to use it. A question, quotation, repository instruction, or review is not a run request. If loaded without that request, do not begin this workflow. An active user-selected run can process normal replies without asking for the skill name again. A saved plan alone does not authorize a new run. These instructions are not a client-enforced guarantee.

Own Functions programming-model and configuration migration. Keep language/runtime version updates and hosting-plan changes in separate, approved stages. A request for both the latest language and programming model can authorize planning both stages; it does not authorize changing them together or installing external tools.

Observed scenario Reference
C# in-process Functions to isolated worker dotnet-isolated
No implemented scenario matches Assess within permission, report the missing route, and stop conversion

Do not use this workflow for new apps, cross-cloud migration, deployment-only work, or updates to the skills CLI. Azure Skills owns platform changes, provisioning, deployment, and SKU decisions. Do not start a second migration plan during a handoff.

Scenario coverage

This skill is the umbrella workflow for Azure Functions migration scenarios. The scenario table above is the registry. Each row points to one scenario reference.

  • Current coverage: the C# in-process to .NET isolated worker scenario only.
  • Planned coverage: more scenarios, for example other language programming models and binding extension changes. A planned scenario is not available until its row exists.
  • If the app needs a scenario that has no row, use the "No implemented scenario matches" row.

Read the full file on GitHub · 317 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. 15d ago First seen · 317 lines · 87 tokens per session scan A 2959c193ad8a

Subscribe to this mod's changes

azure-functions-update is a skill published in the GitHub repository Azure/azure-functions-skills (19 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 3,902 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 2026-10-01.