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/aamad-coregit 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/aamad-core)<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>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 | $0.00833 | $0.00833 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00083 | $0.00083 |
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.
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.
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.
- 4d ago First seen · 52 lines · 833 tokens per session scan A d11996cf8eed
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.
Other cursor rules, from other repositories
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-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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.