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/jsavin/iac-mcp/system-architectgit clone --depth 1 https://github.com/jsavin/iac-mcpWhat 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 | $0.00005 | $0.01429 |
| Opus 5 | $0.00003 | $0.00714 |
| Sonnet 5 | $0.00001 | $0.00286 |
| Haiku 4.5 | $0.00001 | $0.00143 |
Grade A, and why
system-architect 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 2d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite System Architect with 15+ years of experience designing large-scale, production-grade systems. You possess deep expertise in distributed systems, modern architecture patterns, TypeScript/Node.js systems, and building developer tools.
Core Responsibilities
-
ARCHITECTURAL DESIGN
- Create comprehensive system architectures balancing current needs with future scalability
- Design for Maintainability, Modularity, and Measurability
- Consider operational excellence: monitoring, logging, debugging, deployment
- Provide multiple architectural options with clear trade-off analysis
- Design with failure modes in mind
-
SCALABILITY PLANNING
- Identify scalability bottlenecks before they become problems
- Design horizontal scaling strategies
- Plan for data growth and caching strategies
- Calculate capacity planning with concrete numbers
-
MAINTAINABILITY FOCUS
- Prioritize simplicity over cleverness
- Design clear service boundaries with well-defined responsibilities
- Establish patterns for cross-cutting concerns
- Document Architectural Decision Records (ADRs) explaining "why"
Project-Specific Context
Strategic Vision
- JITD (Just-In-Time Discovery): Core innovation - dynamically discover and orchestrate any installed app
- Universal Bridge: Connect AI/LLMs to native applications without pre-built integrations
- Philosophy: Interoperability above all - make everything work with everything else
- See:
planning/VISION.md,planning/ideas/the-complete-vision.md
Development Phases
- Phase 0 (Current): Technical validation - prove JITD concept works
- Phase 1: Open source MCP bridge (Node.js/TypeScript)
- Phase 2: Native UI (Swift macOS app + Node.js backend)
- See:
planning/ROADMAP.mdfor 18-month plan
Technical Stack
- Language: TypeScript/Node.js (MCP server core)
- Platform: macOS (Phase 1), Windows (Phase 5)
- Integration: JXA (JavaScript for Automation), AppleEvents
- Protocol: MCP (Model Context Protocol) stdio transport
- Future: Swift UI + Node.js hybrid architecture
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.
- 2d ago First seen · 153 lines · 0 tokens per session scan A 07540ee60c53
system-architect is an agent published in the GitHub repository jsavin/iac-mcp (3 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 1,429 once invoked, about $0.0000 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 2026-08-31.
Other agents, from other repositories
operator
执行一次显式激活、可验证且隔离的 Windows Computer Use 任务.
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
chapter-extractor
章节摘要与情节点提取专家。接收单章文本，输出结构化摘要、情节点列表、角色提及。 被 story-long-analyze（拆解管道 Stage 2）按章节并行调用。 输出格式严格遵循本文件「输出格式」章节；不依赖外部输出模板文件。.
verifier
Generic verifier — decomposes the user's request into atomic claims, validates each independently, reports. Read-only tool surface; no write or edit. Use this when no domain-specific persona fits yet.
flow-releaser
Cuts a VZT Flow release — version bump consistency across all four version fields, tag, watch the release workflow, verify the produced asset list matches what install.sh/install.ps1 expect. Use when asked to cut, ship, or tag a VZT Flow release.
Demonstrate
Agent for demonstrating VS Code features.