azure-sdk-for-net: Skill for Claude Code

.github/skills/auto-build-repair/SKILL.md

auto-build-repair is a skill for Claude Code, Codex from Azure/azure-sdk-for-net. It costs 149 tokens per session (3,813 once invoked), scanned A, original, MIT.

An automated repair loop for an existing Azure SDK pull request whose custom code causes the build to fail. It repeatedly applies the shared repair process within a language-specific limit.

In plain words
What is it for?
It is for repairing labeled Azure SDK pull requests after code generation, until the package builds or the allowed repair attempts are used.
Why use it?
It fixes build failures caused by custom code no longer matching regenerated SDK code, without requiring manual edits.

Skill for Claude CodeCodex ✓ vendor

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

This is Azure/azure-sdk-for-net's own configuration. It tells Claude Code and Codex how to work on azure-sdk-for-net itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything azure-sdk-for-net configures →

About the project

Azure SDK for .NET is a repository containing the actively developed C# libraries that applications use to work with Azure services. It is for .NET developers building software that connects to Azure storage, management, and other cloud services.

Azure/azure-sdk-for-net · 6,050 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to Azure/azure-sdk-for-net. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Azure/azure-sdk-for-net/main/.github/skills/auto-build-repair/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Azure/azure-sdk-for-net

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 auto-build-repair

README.md
[![agentmods](https://agentmods.dev/badge/skills/azure/azure-sdk-for-net/auto-build-repair/github.svg)](https://agentmods.dev/skills/azure/azure-sdk-for-net/auto-build-repair)
Your own site
<a href="https://agentmods.dev/skills/azure/azure-sdk-for-net/auto-build-repair"><img src="https://agentmods.dev/badge/skills/azure/azure-sdk-for-net/auto-build-repair/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 auto-build-repair

Your own site · 80×15
<a href="https://agentmods.dev/skills/azure/azure-sdk-for-net/auto-build-repair"><img src="https://agentmods.dev/badge/skills/azure/azure-sdk-for-net/auto-build-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,813 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: 4 findings, 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 15
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 15
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 130
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • low Excessive Agency · line 73
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 $0.00149 $0.03813
Opus 5 $0.00075 $0.01906
Sonnet 5 $0.00030 $0.00763
Haiku 4.5 $0.00015 $0.00381

Measured 7d ago against content hash 1f83b163635a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

auto-build-repair 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 7d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (emit-repair-report.ps1, test/emit-repair-report.tests.ps1, test/sdk-build-repair-push-gate.tests.ps1, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/auto-build-repair/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Build Repair

Purpose-built, headless skill that repairs an already-generated Azure SDK pull request whose build fails because of custom (non-generated) code that has drifted from the regenerated surface.

This is NOT a migration. The SDK PR already exists, the TypeSpec source is already pinned via tsp-location.yaml, and most of the diff is generated code. Your only job is to drive the shared azure-sdk-mcp:azsdk_customized_code_update engine — in custom-code-only scope (editScope: CustomCode) — re-invoking it up to maxIterations times (a cross-language repair bound; its per-language value is read from repair-config.yml, see Bounds) until the package builds, then stop. Do not hand-edit code and do not use any other fix engine (e.g. the per-language generator-agent); the cross-language design centralizes the fix logic in this one shared tool.

When Invoked

The Copilot cloud agent runs this skill on an Auto SDK PR created by the release-planner generation flow and labeled auto-sdk-build-fix. Trigger phrases: "auto build repair", "repair build", "fix the SDK PR build", "auto-sdk-build-fix", "custom-code build repair".

This skill runs non-interactively in an ephemeral environment. Never prompt the user for input (no spec repo path, no confirmations). If you cannot proceed within scope, stop and emit structured guidance (see Stop Conditions).

The engine: azure-sdk-mcp:azsdk_customized_code_update

This skill is a thin wrapper. All classification → fix → regenerate → rebuild logic lives inside the shared azure-sdk-mcp:azsdk_customized_code_update tool, which already handles .NET (partial classes / [CodeGen*]), Python (_patch.py), and Java (*Customization.java). Do not replicate its behavior by editing files yourself, and do not invoke a per-language generator-agent — the design deliberately uses this single shared engine.

Requires azsdk ≥ 0.6.22 — the editScope parameter (and optional tspProjectPath) used below shipped in azsdk-cli 0.6.22. The cloud agent installs the MCP tool via eng/common/mcp/azure-sdk-mcp.ps1, which defaults to the latest release, so this is satisfied automatically; no version pin needs bumping.

Read the full file on GitHub · 133 lines

Files

What ships with it

8 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.

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. 7d ago Changed 1f83b163635a
  2. 12d ago First seen · 133 lines · 149 tokens per session scan A 149c1db4fd51

Subscribe to this mod's changes

auto-build-repair is a skill published in the GitHub repository Azure/azure-sdk-for-net (6,050 stars, last pushed yesterday), licensed MIT. It adds 149 tokens to every session and 3,813 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

cosmos-design-struct

Enforce consistent struct design conventions across sdk/cosmos crates. Validates visibility modifiers, field privacy, #[nonexhaustive] usage, and construction API patterns (Default/new with with setters, or optional separate builders with builder()/build()), and construction correctness on public structs. Can auto-fix…

Azure/azure-sdk-for-rust · 83 tokens

cosmos-pre-commit-validation

Run pre-commit checks for a specific set of crates. Use this when validating changes under sdk/cosmos before committing or during code review.

Azure/azure-sdk-for-rust · 35 tokens

azure-messaging

Troubleshoot and resolve issues with Azure Messaging SDKs for Event Hubs and Service Bus. Covers connection failures, authentication errors, message processing issues, and SDK configuration problems. WHEN: event hub SDK error, service bus SDK issue, messaging connection failure, AMQP error, event processor host issue…

microsoft/skills · 178 tokens

cu-sdk-setup

Guide SDK users through setting up their Java environment for Azure AI Content Understanding. Use this skill when users need help installing the SDK, configuring Azure resources, deploying required models, setting environment variables, or running samples.

Azure/azure-sdk-for-java · 47 tokens

sap-background-jobs

Investigate SAP background jobs, including failed or aborted jobs, job status, job steps, job logs, runtime dumps, TBTCO, TBTCP, and TBTCJOBLOG0-9.

marcellourbani/vscode_abap_remote_fs · 46 tokens

chrome-devtools-mcp

Use Chrome DevTools MCP from .NET agents and .NET-focused repos to inspect, debug, and automate Chrome through an MCP client. USE FOR: the repo needs browser-level debugging for ASP.NET Core, Blazor, WebAssembly, or any .NET app with a web UI; the user wants an MCP server that can inspect console. DO NOT USE FOR: pure…

managedcode/dotnet-skills · 130 tokens