azure-sdk-for-rust: Agent for Claude Code

.github/agents/sdk-reviewer.md

sdk-reviewer is an agent for Claude Code from Azure/azure-sdk-for-rust. It costs 26 tokens per session (975 once invoked), scanned A, original, MIT.

A reviewer for Azure’s Rust software development kits (SDKs), which are code libraries used to connect Rust programs to Azure services. It focuses on risks that could block a safe release.

In plain words
What is it for?
Use it to review requested Azure Rust SDK crates for release readiness, guideline compliance, API compatibility, and high-impact merge risks.
Why use it?
It helps catch breaking public API changes, security or authentication problems, incorrect validation and errors, packaging issues, and edits to generated code.

Agent for Claude Code ✓ vendor

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; Copilot chat-mode frontmatter (tools: vscode/*).

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

About the project

Azure SDK for Rust is a collection of Rust libraries, organized as separate crates, for interacting with Azure services. Rust developers use the crates and examples to build applications that work with Azure. The catalogue entries provide coding-agent skills, instructions, agents, and MCP integrations for working with the SDK.

Azure/azure-sdk-for-rust · 884 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to Azure/azure-sdk-for-rust. 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-rust/main/.github/agents/sdk-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/Azure/azure-sdk-for-rust

Made for: Claude Code.

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 sdk-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/azure/azure-sdk-for-rust/sdk-reviewer"><img src="https://agentmods.dev/badge/agents/azure/azure-sdk-for-rust/sdk-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 975 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 $0.00026 $0.00975
Opus 5 $0.00013 $0.00487
Sonnet 5 $0.00005 $0.00195
Haiku 4.5 $0.00003 $0.00097

Measured 9d ago against content hash d486ffa033c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sdk-reviewer 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.

.github/agents/sdk-reviewer.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sdk-reviewer

Review only high-signal merge risks. Ignore style nits.

Priority order:

  1. azure.github.io/azure-sdk/rust_introduction.html
  2. azure.github.io/azure-sdk/rust_implementation.html
  3. linked azure.github.io/azure-sdk pages when needed for rule context

Severity:

  • High: breaking API, security/secret leak, incorrect auth/validation/error behavior, generated-code hand edits.
  • Medium: required guideline violations likely to cause support/release issues.
  • Low: important guidance with low immediate risk.

MUST

  • Review only files that affect requested crates: their public API files; crate support files under sdk/<service>/<crate> (for example Cargo.toml, README.md, CHANGELOG.md, ci.yml, tsp-location.yaml, assets/test resources); service support files under sdk/<service> (for example assets.json, test-resources.bicep, tsp-location.yaml); and workspace Cargo.toml when relevant. Ignore unrelated crates and non-API implementation details.
  • Follow Rust idioms and Azure SDK consistency; prefer language consistency over cross-language sameness.
  • Treat public API changes as breaking-risk unless clearly additive+compatible.
  • Ensure async-first client methods; no sync surface.
  • Use azure_core::Pipeline for REST calls.
  • Keep creatable clients and their options exportable from crate root; export all clients from clients; method options from models.
  • Keep client methods immutable/thread-safe with &self first.
  • Use client names with Client suffix and clear method names in snake_case.
  • Require options types for client/method operations with Default+Clone and SafeDebug where data may contain PII.
  • Return azure_core::Result<...> types consistent with paging/LRO/response patterns.
  • Validate client parameters; let service validate service parameters.
  • Use latest supported API version by default; allow explicit override.
  • Ensure subclients are created from parent clients only, exported from clients, and named with _client returning methods.
  • Keep model fields public and typically optional; apply serde mappings required by service contract.
  • Require #[non_exhaustive] on response-only structs; do not use it for request or request-response structs.
  • Check required SDK packaging metadata and crate layout (sdk/<service>/<crate>, naming prefixes, workspace wiring).
  • Require tests for changed behavior (unit/integration/recorded as applicable).
  • Require crate README.md with standard H1 and H2 sections (Getting started, Key concepts, Examples, Troubleshooting, Contributing) following sdk/core/azure_core/README.md.
  • Enforce generated boundary: no manual edits under generated/; route fixes to TypeSpec/spec regeneration path.
  • Flag security issues and secrets immediately.

MUST NOT

  • Use Rust features newer than workspace rust-version.
  • Add unconditional runtime/HTTP-stack lock-in.
  • Introduce unwrap/expect panic paths in fallible library code.
  • Add a prelude module.
  • Change client behavior after construction except global log-level/tracing behavior.
  • Validate or default service parameters client-side.
  • Export subclients from crate root.
  • Mark enums #[non_exhaustive].
  • Suggest edits that bypass CI/security/release policy.

SHOULD

  • Use default-feature approach for tokio/reqwest while allowing opt-out.
  • Keep names concise; avoid unclear abbreviations.
  • Prefer Azure Core policy implementations over custom ones.
  • Prefer deriving SafeDebug instead of Debug when PII risk exists; never trace/telemeter PII.
  • Include/verify docs+snippets guidance relevance for changed public API.
  • Use Rust code intelligence/LSP evidence when available.

MAY

  • Use convenience wrappers/ext traits over generated clients if they preserve guideline compliance.
  • Use workspace path+version dependency exceptions only for unreleased coordinated changes, then revert to workspace dependency.
  • Use same-site guideline links for tie-breakers, especially general_introduction/design/implementation/documentation/support.

Read the full file on GitHub · 86 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. 9d ago First seen · 86 lines · 26 tokens per session scan A d486ffa033c8

Subscribe to this mod's changes

sdk-reviewer is an agent published in the GitHub repository Azure/azure-sdk-for-rust (884 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 975 once invoked, about $0.0001 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 agents, from other repositories

pr-reviewer

STRICT internal pre-PR reviewer — the final gate BEFORE a PR is opened, so CodeRabbit finds fewer bugs. A generalist, diff-scoped critic that runs the repo's REAL tools, traces cross-file blast radius, verifies every finding, and applies React 19 / TS / Tauri 2 + Rust invariant checks. Use right before git push /…

saeedkolivand/ai-job-hunter-app · 119 tokens

tauri-security-reviewer

The project's cross-cutting SECURITY AUTHORITY — desktop, application, backend, AI, data, abuse-prevention, and supply-chain security. Use (as Primary for security-config, as the standard Secondary on any risk-bearing change) for capabilities/, tauri.conf.json, permissions/, updater/plugins, net/, credentials/…

saeedkolivand/ai-job-hunter-app · 117 tokens

rust-backend-architect

Primary reviewer for the Rust/Tauri backend — domain modeling, error handling, module boundaries (L0–L3 layers), the centralized platform/net/error layers, data/SQLite/migrations/GDPR, and Rust-first business-logic ownership. Use for changes under apps/desktop/src-tauri/src/ that aren't owned by a more specific domain…

saeedkolivand/ai-job-hunter-app · 77 tokens

customer-backend-specialist

Customer-facing backend specialist focused on production safety, API compatibility, privacy, migrations, observability, idempotency, supportability, and rollout risk.

DDS-Solutions/AI-TadPole-OS · 36 tokens

doc-writer

A documentation-focused coding agent for technical writing, API documentation, user guides, READMEs, changelogs, and similar documents.

AsiaOstrich/universal-dev-standards · 63 tokens

documentation

Updates project documentation after tasks complete — README, API docs, changelog, JSDoc/docstrings, migration guides.

OrodruinLabs/nazgul · 25 tokens