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.
npx agentmods add rules/synaptic-ai-consulting/aamad/adapter-claude-agent-sdkgit clone --depth 1 https://github.com/synaptic-ai-consulting/AAMADWrote 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.
[](https://agentmods.dev/rules/synaptic-ai-consulting/aamad/adapter-claude-agent-sdk)<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>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.
| Model | Per session | Once 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 |
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.
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.
- Python:
- Configure required runtime environment variables (
ANTHROPIC_API_KEYand 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
AgentDefinitionentries inClaudeAgentOptions.agents. - Use the main runtime agent as coordinator and invoke specialized agents via the
Agenttool. - 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
ClaudeSDKClientfor 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_toolslists 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/logsand redact sensitive values.
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.
- 6d ago First seen · 51 lines · 564 tokens per session scan A 817ca6126a08
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.