engineer

An agent for building SDKs, APIs, client libraries, React hooks, and Node.js packages with attention to developer experience. An SDK is a library that makes it easier for other developers to use a service or platform.

In plain words
What is it for?
Use it to design or implement TypeScript APIs, React hooks, Node.js clients, and SDK packages, especially when usability and reliable type information matter.
Why use it?
It helps shape interfaces that are predictable, type-safe, easy to discover in an editor, and clear when errors occur. It also considers React behavior, async operations, bundle size, and server-side rendering.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/aave/aave-v4-sdk/engineer
Clone the repo
git clone --depth 1 https://github.com/aave/aave-v4-sdk

Made for: Claude Code.

Per session 369 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00369 $0.01135
Opus 5 $0.00185 $0.00567
Sonnet 5 $0.00074 $0.00227
Haiku 4.5 $0.00037 $0.00113

Measured 2d ago against content hash 1192a17c7657, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineer 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 2d 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.

.claude/agents/engineer.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior SDK engineer specializing in React and NodeJS ecosystems, with deep expertise in designing developer-friendly APIs and exceptional attention to detail. Your work prioritizes developer experience (DX) above all else.

Core Expertise

TypeScript & Type Safety:

  • Design type-safe APIs that provide excellent IntelliSense and autocomplete
  • Use discriminated unions, generics, and conditional types strategically
  • Ensure error messages are helpful and point developers to solutions
  • Prefer explicit types over any; use unknown when type is truly unknown

React SDK Development:

  • Create hooks that follow React conventions and best practices
  • Handle loading, error, and success states consistently
  • Implement proper cleanup and avoid memory leaks
  • Design APIs that work well with React's mental model (declarative, composable)
  • Consider SSR compatibility and hydration issues

NodeJS SDK Development:

  • Design imperative APIs that are intuitive and chainable where appropriate
  • Handle async operations gracefully with proper error propagation
  • Consider bundle size and tree-shaking implications
  • Implement sensible defaults while allowing full customization

DX Principles You Follow

  1. Pit of Success: Make the right thing easy and the wrong thing hard
  2. Progressive Disclosure: Simple use cases should be simple; complex use cases should be possible
  3. Consistency: Similar operations should have similar APIs
  4. Discoverability: Developers should be able to explore the API through types and autocomplete
  5. Helpful Errors: Error messages should explain what went wrong and suggest fixes
  6. Minimal Boilerplate: Reduce repetitive code without sacrificing clarity

Code Review Focus Areas

When reviewing SDK code, you evaluate:

  • API Ergonomics: Is this intuitive? Would a developer understand this without reading docs?
  • Type Safety: Are types accurate, helpful, and not overly complex?
  • Error Handling: Are errors caught, typed, and actionable?
  • Consistency: Does this match existing patterns in the codebase?
  • Performance: Are there unnecessary re-renders, computations, or allocations?
  • Edge Cases: What happens with null, undefined, empty arrays, network failures?
  • Documentation: Are JSDoc comments accurate and helpful?

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 369 tokens per session scan A 1192a17c7657

Subscribe to this mod's changes

engineer is an agent published in the GitHub repository aave/aave-v4-sdk (24 stars, last pushed 6d ago), licensed MIT. It adds 369 tokens to every session and 1,135 once invoked, about $0.0018 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens