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

.github/skills/code-review/SKILL.md

code-review is a skill for Claude Code, Codex from Azure/azure-sdk-for-go. It costs 86 tokens per session (4,447 once invoked), scanned A, original, MIT.

A code-review guide for the Azure SDK for Go repository. It checks proposed changes, such as Go code, documentation, samples, and CI files, against that project's rules before they are merged.

In plain words
What is it for?
Use it when reviewing pull requests in the Azure SDK for Go, including API design, error handling, models, documentation, and build or CI changes.
Why use it?
It focuses review comments on issues maintainers would actually require people to fix. It also prevents unnecessary comments on generated code and follows repository-specific instructions when they differ from general guidance.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

This is Azure/azure-sdk-for-go's own configuration. It tells Claude Code and Codex how to work on azure-sdk-for-go 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-go configures →

About the project

Azure SDK for Go is a collection of Go modules for using and managing Microsoft Azure services through code. Go developers use client modules to work with existing Azure resources and management modules to configure those resources. Its catalogue add-ons provide instructions and agent support for developing within the SDK repository.

Azure/azure-sdk-for-go · 1,857 stars · on GitHub · docs.microsoft.com

Reuse

Borrowing it

Nothing to install: this file belongs to Azure/azure-sdk-for-go. 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-go/main/.github/skills/code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Azure/azure-sdk-for-go

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 code-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/azure/azure-sdk-for-go/code-review"><img src="https://agentmods.dev/badge/skills/azure/azure-sdk-for-go/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,447 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 $0.00086 $0.04447
Opus 5.5 $0.00034 $0.01779
Sonnet 5.5 $0.00017 $0.00889
Haiku 4.5 $0.00009 $0.00445

Measured 21d ago against content hash 4af7a7176738, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-review 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 21d 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/skills/code-review/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azure SDK for Go Code Review

Review changes against the Azure SDK for Go design guidelines and implementation guidelines, together with AGENTS.md, CONTRIBUTING.md, and the repository Copilot instructions.

Repository-specific instructions win. Where this skill or a file under .github/instructions/ contradicts the published guidelines, follow the repository. The published guidelines describe the cross-language ideal; this repo has deliberate exceptions.

Comment only on issues that a Go SDK maintainer would ask to change before merging.

Step 0 — Decide whether to comment at all

Before writing any comment, run through this gate. If any item applies, stay silent.

  1. Generated code. If the file contains a DO NOT EDIT. code-generation marker (emitted by both the current Go Code Generator and the retired AutoRest generator), do not comment on style, naming, doc comments, example values, constants, or any pattern listed in .github/instructions/go-code.instructions.md. Only report a clear, demonstrable bug not covered by those rules. When in doubt, say nothing — the fix belongs in azure-rest-api-specs or the emitter, not in this repo. Never suggest editing generated output directly; it is overwritten on regeneration. Point the fix at the source spec, the generator inputs (e.g. tsp-location.yaml), or the generator itself — see generation guidance. Files that are generated but intentionally hand-maintained, such as version.go, omit this marker so their version const can be updated; treat them as regular editable code.

    The one exception is acronym casing (see "Naming and file conventions" below). Go uppercases acronyms in exported identifiers while most other languages don't, so these are routinely missed upstream. Flag them on generated code too, for types, struct fields, methods, enum/constant member names, and function parameters — userId string should be userID string. Parameters aren't public surface, but leaving them inconsistent looks sloppy and spreads. Because generated files are overwritten, the comment must say the fix belongs upstream in azure-rest-api-specs (via a client-name customization such as @clientName), not in this repository. Never suggest editing the generated file directly.

Read the full file on GitHub · 287 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. 21d ago First seen · 287 lines · 86 tokens per session scan A 4af7a7176738

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository Azure/azure-sdk-for-go (1,857 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 4,447 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 2026-10-03.

Related

Other skills, from other repositories

generate-code-cs

Generate the code from typespec for C#. Parameter: C# SDK repository root location .

Azure/azure-sdk-for-net · 26 tokens

translate-a-sample

Translate the Azure SDK sample from python to C# and generate markdownn file for the sample. Parameters: C# SDK repository root; python SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; The name of sample file in Python SDK repository.

Azure/azure-sdk-for-net · 90 tokens

author-test

Generate a test given sample. Parameters: C# SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; the sample to use as a starting point for the test.

Azure/azure-sdk-for-net · 68 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

design-review

Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.

dimetron/pi-go · 30 tokens

agents-md

Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Use this skill whenever the user asks to create, scaffold, bootstrap, update, or review an AGENTS.md (or agent-instructions, CLAUDE.md, repo guide for agents) file in a codebase. Also trigger when the user says "add AGENTS.md", "make this repo…

dimetron/pi-go · 138 tokens