adapter-registry

adapter-registry is a cursor rule for Cursor from synaptic-ai-consulting/AAMAD. It costs 512 tokens per session, scanned A, original, Apache-2.0.

A set of rules for selecting the runtime used by a generated multi-agent application. A runtime is the software environment that runs the agents; supported choices include CrewAI, Claude Agent SDK, and Cursor SDK.

In plain words
What is it for?
Use it to select a runtime through an environment variable and define the setup, agents, tools, execution limits, logging, sessions, and output rules that runtime must follow.
Why use it?
It lets a project choose its execution environment without changing the main workflow. It also records the selected choice and warns when the setting is missing or unknown.

Cursor rule for 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-registry
Clone the repo
git clone --depth 1 https://github.com/synaptic-ai-consulting/AAMAD

Made for: 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-registry

README.md
[![agentmods](https://agentmods.dev/badge/rules/synaptic-ai-consulting/aamad/adapter-registry.svg)](https://agentmods.dev/rules/synaptic-ai-consulting/aamad/adapter-registry)
Your own site
<a href="https://agentmods.dev/rules/synaptic-ai-consulting/aamad/adapter-registry"><img src="https://agentmods.dev/badge/rules/synaptic-ai-consulting/aamad/adapter-registry.svg" alt="Measured on agentmods" height="20"></a>
Per session 512 This file is loaded in full into every session.
When invoked 512 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 $0.00512 $0.00512
Opus 5 $0.00256 $0.00256
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 4d ago against content hash 66466350652c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adapter-registry 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 4d 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-registry.mdc · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adapter Registry Rules

Purpose

  • Select the runtime target for the generated multi-agent application without changing AAMAD's core crew workflow.

Selection Mechanism

  • Use environment variable AAMAD_TARGET_RUNTIME with values:
    • crewai (default)
    • claude-agent-sdk
    • cursor-sdk
  • Runtime adapter rules are loaded from .cursor/rules/adapter-<name>.mdc; selected runtime should have a matching adapter file.
  • If unset or unknown, default to crewai and record the resolved value plus warning in the artifact Audit.

Adapter Contract

  • Each adapter must define:
    • Setup requirements (dependencies, env vars, and runtime prerequisites).
    • Agent declaration pattern for the generated application (how runtime agents/subagents are represented).
    • Tool and MCP binding policy, including validation and least-privilege guidance.
    • Execution controls (iteration/time/budget caps, retries, and cancellation behavior).
    • Logging hooks for Prompt Trace, Diagnostic, and Audit sections.
    • Memory/session handling and reproducibility constraints.
    • Output contract conventions (structured I/O, schema checks, citation/grounding rules when applicable).

Runtime Hooks

  • Preflight: verify PRD/SAD/SFS presence per persona, validate runtime/tool config, resolve runtime value, then proceed or Halt and Report.
  • Postflight: validate artifact against template schema, append Prompt Trace + Audit, ensure deterministic write.

Extensibility

  • New adapters must keep the same section taxonomy: Purpose, Setup, Mapping, Execution, Tools, Logging, Quality Gates, Failure Policy.
  • Adapters may add capabilities (e.g., graph supervision) but cannot change AAMAD Core contracts.

Selection Criteria

  • crewai: best when you want declarative task orchestration with YAML-first config and explicit task graph controls.
  • claude-agent-sdk: best when you want an agentic runtime harness with hooks, custom tools/MCP integration, and session-level control.
  • cursor-sdk: best when you want TypeScript-first runtime integration with Cursor-native harness capabilities and explicit tool/runtime contracts.

Read the full file on GitHub · 46 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. 4d ago First seen · 46 lines · 512 tokens per session scan A 66466350652c

Subscribe to this mod's changes

adapter-registry is a cursor rule published in the GitHub repository synaptic-ai-consulting/AAMAD (80 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 512 tokens to every session, about $0.0026 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.