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 skills add batterfried-philosophy172/Agent-Startup-Skills --skill system-architectgit clone --depth 1 https://github.com/batterfried-philosophy172/Agent-Startup-SkillsWrote 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/skills/batterfried-philosophy172/agent-startup-skills/system-architect)<a href="https://agentmods.dev/skills/batterfried-philosophy172/agent-startup-skills/system-architect"><img src="https://agentmods.dev/badge/skills/batterfried-philosophy172/agent-startup-skills/system-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/batterfried-philosophy172/agent-startup-skills/system-architect"><img src="https://agentmods.dev/badge/skills/batterfried-philosophy172/agent-startup-skills/system-architect.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00044 | $0.00622 |
| Opus 5 | $0.00022 | $0.00311 |
| Sonnet 5 | $0.00009 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
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 11d 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.
This is a copy
100% identical to system-architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Architect — Design Agent
Purpose
Design a complete, justified system architecture before any code is written. Prevent "spaghetti architecture" by making deliberate, documented choices.
When to Use
- After MVP scope is approved
- When choosing a tech stack for a new project
- When designing API contracts or system structure
Process
Step 1: Tech Stack Selection
For each layer, recommend a technology with a one-line justification:
| Layer | Choice | Why |
|---|---|---|
| Frontend | e.g., Next.js | SSR for SEO, React ecosystem |
| Backend | e.g., Next.js API Routes | Unified codebase, serverless-ready |
| Database | e.g., PostgreSQL | Relational data, free tier on Supabase |
| Auth | e.g., NextAuth.js | Free, supports OAuth providers |
| Hosting | e.g., Vercel | Free tier, zero-config deploys |
Constraint: Prefer free-tier-friendly technologies unless the user specifies a budget.
Step 2: System Architecture
Describe the architecture in plain text or a mermaid diagram:
- How do the frontend, backend, and database connect?
- What is the request flow for the core user action?
- Where does authentication happen?
Step 3: Project File Structure
Present the complete folder/file tree:
project-root/
├── src/
│ ├── app/ # Pages and routes
│ ├── components/ # Reusable UI components
│ ├── lib/ # Business logic and utilities
│ ├── api/ # API route handlers
│ └── db/ # Database schema and migrations
├── tests/ # Test files
├── public/ # Static assets
├── .env.example # Environment variable template
├── package.json
└── README.md
Step 4: API Endpoint Inventory
List every API endpoint the MVP needs:
| Method | Endpoint | Description | Auth Required |
|---|---|---|---|
| POST | /api/auth/register | Create new user | No |
| POST | /api/auth/login | Authenticate user | No |
| GET | /api/[resource] | List resources | Yes |
Step 5: External Services
List any third-party services required:
- What it does, why it's needed, what it costs, and the free tier limits
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.
- 11d ago First seen · 81 lines · 44 tokens per session scan A 2697489ae4fb
system-architect is a skill published in the GitHub repository batterfried-philosophy172/Agent-Startup-Skills (2 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 622 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to system-architect, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ash-framework
Ash Framework — resources, actions, policies, aggregates, calculations, AshPhoenix.Form, LiveView, migrations. Use when generating resources via mix ash.codegen, editing changes, checks, types, validations, or domain code interfaces.
deploy
Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays. Use when configuring Fly.io, Docker, CI/CD, health checks, or production migrations.
liveview-patterns
Build LiveView: async data (assignasync), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, livepatch. Use when handling interactions, debugging events, or tracking Presence.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
oban
Oban job processing — workers, perform/1 (OSS) and process/1 (Pro), queues, cron, retries, unique jobs, idempotency, Oban Pro (Workflow, Batch, Chunk, Smart Engine), Testing. Use when writing Oban workers, queue config, or debugging jobs.
perf
Analyze Elixir/Phoenix performance — N+1 queries, assign bloat, ecto optimization, genserver bottlenecks. Use when slowness, timeouts, or high memory reported.