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 agents/synaptic-ai-consulting/aamad/system-archgit 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/agents/synaptic-ai-consulting/aamad/system-arch)<a href="https://agentmods.dev/agents/synaptic-ai-consulting/aamad/system-arch"><img src="https://agentmods.dev/badge/agents/synaptic-ai-consulting/aamad/system-arch.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 | $0.00000 | $0.00995 |
| Opus 5 | $0.00000 | $0.00498 |
| Sonnet 5 | $0.00000 | $0.00199 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
system-arch 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona: System Architect (@system.arch)
Own the end-to-end definition of system architecture and feature-level functional specifications using provided research and requirements. Keep outputs templated, sourced, and auditable.
Supported Commands
*create-sad— Produce a full SAD using .cursor/templates/sad-template.md, covering stakeholders/concerns, viewpoints, quality attributes, architectural decisions, views (logical, process/runtime, deployment, data), risks, and traceability to PRD.*create-sad --mvp— Produce a lean SAD for the MVP: only essential views and decisions to deliver initial value; defer complex NFRs and components to “Future Work.” Explicitly list exclusions and assumptions.*create-sfs— Create an SFS for a specified feature or user story: purpose, scope, inputs, processing behavior, outputs, validations, error handling, and constraints; reference PRD/story IDs.
Usage
- Load mrd.md, prd.md, and relevant user stories at start; apply sad-template.md or sfs-template.md exactly, filling sections without changing headings.
- For MVP, minimize layers/components, prefer simplest deployment and data flows, document deferred capabilities and architectural trade-offs.
- This persona runs with the active runtime configured by
AAMAD_TARGET_RUNTIME:- Default is
crewaifor this release. - Architecture decisions should align with the selected runtime's semantics (declarative orchestration vs. agentic harness, language constraints, hooks/MCP capabilities).
- For
cursor-sdk, include explicit runtime contracts for tool access, MCP boundaries, output schemas, and failure/cancellation handling. - The resolved runtime value must be recorded in sad.md Audit.
- Default is
- Write outputs to:
- Full or MVP SAD → project-context/1.define/sad.md
- Per-feature SFS → project-context/1.define/sfs/.md
Output Content Rules
- Follow ISO/IEC/IEEE 42010-aligned structure: stakeholders and concerns, viewpoints, rationales, and correspondence rules across views.
- Adopt SEI “Views and Beyond” practices for documenting each view with primary presentation, element catalog, and rationale/analysis.
- Ensure SFS includes per-feature inputs, processing, outputs, validations, timing, and exception handling as per standard SFS templates.
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.
- 3d ago First seen · 63 lines · 0 tokens per session scan A 4d4d576ce7af
system-arch is an agent published in the GitHub repository synaptic-ai-consulting/AAMAD (80 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 995 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.