aamad-core

aamad-core is a cursor rule for Cursor from synaptic-ai-consulting/AAMAD. It costs 833 tokens per session, scanned A, original, Apache-2.0.

Repository-wide rules for AAMAD, a system where specialized AI personas collaborate on software artifacts.

In plain words
What is it for?
Use them to define agent contracts, task contracts, artifact sources and assumptions, permitted actions, audit records, and minimal first versions.
Why use it?
They clarify ownership, allowed inputs and outputs, traceability, reproducibility, and what to do when requirements are missing or unclear.

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/aamad-core
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 aamad-core

README.md
[![agentmods](https://agentmods.dev/badge/rules/synaptic-ai-consulting/aamad/aamad-core.svg)](https://agentmods.dev/rules/synaptic-ai-consulting/aamad/aamad-core)
Your own site
<a href="https://agentmods.dev/rules/synaptic-ai-consulting/aamad/aamad-core"><img src="https://agentmods.dev/badge/rules/synaptic-ai-consulting/aamad/aamad-core.svg" alt="Measured on agentmods" height="20"></a>
Per session 833 This file is loaded in full into every session.
When invoked 833 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 $0.00833 $0.00833
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 4d ago against content hash d11996cf8eed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aamad-core 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/aamad-core.mdc · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

  • Define universal principles, contracts, and invariants for AI-assisted, multi-agent development, independent of any specific execution framework.

Principles

  • Single responsibility personas: each persona owns a defined epic with explicit inputs, outputs, and prohibited actions.
  • Context-first engineering: all outputs must trace to PRD, SAD, SFS, or user stories; do not invent requirements.
  • Reproducibility and provenance: every artifact includes Sources, Assumptions, and Open Questions sections.
  • Deterministic execution: actions are idempotent; perform temp-write-then-atomic-replace for file outputs.
  • Minimal viable architecture first: implement MVP scope before expanding; document deferrals with rationale.

Agent Contract

  • Personas declare: id, role, instructions, actions, inputs, outputs, prohibited-actions. Agents MUST read only declared inputs and write only to declared outputs.
  • On missing/ambiguous inputs, write Assumptions and Open Questions; do not fabricate content.
  • All actions must append an Audit block with timestamp, persona id, and action name to the artifact.

Task Contract

  • Each task defines: description, expected_output (exact target file path and required headings), acceptance_criteria, traceability to PRD/SAD/SFS anchors.
  • Tasks include a self-check verifying required headings; if missing, write Diagnostic and halt.

Tooling Rules

  • Use only approved file and validation tools provided by the active runtime adapter for the generated application; no direct shell or network unless explicitly authorized by persona.
  • Log tool usage in the artifact, including model, temperature, max_tokens, and any material runtime controls impacting determinism.

State and Output

  • Outputs follow template headings exactly (.cursor/templates). Do not wrap machine-parsed blocks in code fences if templates require raw content.
  • Artifacts end with sections: Sources, Assumptions, Open Questions, Audit.
  • Prompt Trace must be captured for high-risk or production-facing outputs; if omitted, the Audit must state why.

Read the full file on GitHub · 52 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 · 52 lines · 833 tokens per session scan A d11996cf8eed

Subscribe to this mod's changes

aamad-core 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 833 tokens to every session, about $0.0042 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.