adapter-claude-agent-sdk

adapter-claude-agent-sdk is a cursor rule for Claude Code, Cursor from synaptic-ai-consulting/AAMAD. It costs 564 tokens per session, scanned A, original, Apache-2.0.

Rules for building an MVP backend with the Claude Agent SDK, a software kit for running Claude-based agents. They describe setup, agent roles, delegation, execution limits, interactive flows, and audit details.

In plain words
What is it for?
Use them when the Claude Agent SDK is selected as the runtime, including for defining agent entries, coordinating specialized agents, configuring credentials, and setting turn, token, retry, and streaming behavior.
Why use it?
They give a generated application a consistent way to configure and run specialized agents on this SDK. Explicit limits and recorded settings make execution easier to control and review.

Cursor rule for Claude CodeCursor

Written for Claude Code and Cursor: PreToolUse hook event, but also installed under .cursor/.

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 rules/synaptic-ai-consulting/aamad/adapter-claude-agent-sdk
Clone the repo
git clone --depth 1 https://github.com/synaptic-ai-consulting/AAMAD

Made for: Claude Code, Cursor.

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 adapter-claude-agent-sdk

README.md
[![agentmods](https://agentmods.dev/badge/rules/synaptic-ai-consulting/aamad/adapter-claude-agent-sdk.svg)](https://agentmods.dev/rules/synaptic-ai-consulting/aamad/adapter-claude-agent-sdk)
Your own site
<a href="https://agentmods.dev/rules/synaptic-ai-consulting/aamad/adapter-claude-agent-sdk"><img src="https://agentmods.dev/badge/rules/synaptic-ai-consulting/aamad/adapter-claude-agent-sdk.svg" alt="Measured on agentmods" height="20"></a>
Per session 564 This file is loaded in full into every session.
When invoked 564 The same file — it is already loaded in full.
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 5.1 $0.00564 $0.00564
Opus 5 $0.00282 $0.00282
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00056 $0.00056

Measured 6d ago against content hash 817ca6126a08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

adapter-claude-agent-sdk 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 6d 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.

.cursor/rules/adapter-claude-agent-sdk.mdc · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Agent SDK Adapter Rules

Purpose

  • Define runtime-specific guidance when AAMAD_TARGET_RUNTIME=claude-agent-sdk.
  • This adapter governs implementation patterns for generated MVP backends that use the Claude Agent SDK.

Setup

  • Install SDK dependencies for the selected language runtime:
    • Python: pip install claude-agent-sdk
    • TypeScript: install the Claude Agent SDK package used by your org standard.
  • Configure required runtime environment variables (ANTHROPIC_API_KEY and any org-specific gateway/base URL settings).
  • Record SDK version, resolved model, temperature, and token controls in artifact Audit.

Mapping

  • Represent specialized runtime agents as AgentDefinition entries in ClaudeAgentOptions.agents.
  • Use the main runtime agent as coordinator and invoke specialized agents via the Agent tool.
  • For cloud-managed multi-agent orchestration, use callable-agent patterns where appropriate and document delegation boundaries in SAD/backend.md.

Execution

  • Set explicit per-task turn and token budgets; do not rely on implicit defaults.
  • Use ClaudeSDKClient for bidirectional interactive flows and streaming workflows.
  • Define retry and idempotency behavior for runtime actions that may be replayed.
  • Use session resume/fork only when required, and document rationale and retention scope in Audit.

Tools

  • Default to least-privilege allowed_tools lists per runtime task.
  • Use built-in tools (Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch) only where required by scope.
  • Prefer in-process MCP servers for custom internal tools; use external MCP servers when process boundaries are required.
  • Validate MCP server availability and auth before execution; fail fast with Diagnostic on missing dependencies.

Logging

  • Capture Prompt Trace prior to execution and append to artifacts or trace logs per persona output rules.
  • Use hooks (PreToolUse, PostToolUse, SubagentStart, SubagentStop) to log lifecycle events and enforce guardrails.
  • Persist runtime trace logs under project-context/2.build/logs and redact sensitive values.

Read the full file on GitHub · 51 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. 6d ago First seen · 51 lines · 564 tokens per session scan A 817ca6126a08

Subscribe to this mod's changes

adapter-claude-agent-sdk is a cursor rule published in the GitHub repository synaptic-ai-consulting/AAMAD (80 stars, last pushed 2d ago), licensed Apache-2.0. It adds 564 tokens to every session, about $0.0028 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.