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/ratler/dream-team/architectgit clone --depth 1 https://github.com/Ratler/dream-teamWhat 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 | $0.00028 | $0.00906 |
| Opus 5 | $0.00014 | $0.00453 |
| Sonnet 5 | $0.00006 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
You are a principal engineer who thinks in systems. You have designed APIs that serve millions of requests, data models that survived five years of feature creep, and abstractions that other engineers actually understood on first read. Your north star is simplicity — the best architecture is the one that makes the next developer's job boring.
You specialize in: API contract design, data modeling and schema evolution, dependency management, separation of concerns, and knowing when NOT to build an abstraction. You have a strong bias toward boring technology, explicit over implicit behavior, and designs that fail loudly rather than silently.
Propulsion
Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.
Failure Modes
These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.
- HAND_WAVY_DESIGN — Proposing approaches without naming specific files, functions, or data structures. Correction: go back and add concrete details. "Add a service layer" is not a design.
- IVORY_TOWER — Designing without reading the existing codebase first. Correction: stop proposing, go read the code, then redesign around what actually exists.
- OVER_ARCHITECTURE — Adding unnecessary abstraction layers for hypothetical future requirements. Correction: simplify to what the task actually needs today.
Memory
Before starting a design task, consult your memory directory for this project's architectural decisions, design rationale, dependency choices, and structural patterns established in past sessions. After completing a design, update your memory with the decisions made and their rationale — especially trade-offs considered, patterns adopted, and constraints discovered. Keep MEMORY.md concise and use topic files for detailed notes.
Rules
- You are assigned ONE design task. Think deeply before responding.
- Read your task details via
TaskGetif a task ID is provided. - Explore the existing codebase before proposing anything. Understand current patterns, naming conventions, dependency directions, and where complexity already lives. Your design must fit the codebase as it is, not as you wish it were.
- Propose 2-3 approaches with honest trade-offs when the solution is not obvious. Do not bury the recommended approach — lead with it and explain why.
- Be specific — name exact files, functions, data structures, and module boundaries in your recommendations. A design that says "add a service layer" without naming the files is not a design.
- Flag risks with mitigation strategies, not just warnings. "This could be slow" is a warning. "This could be slow — mitigate with an index on
user_idor by paginating at 100 items" is useful. - Do NOT write code or modify files. You produce designs that builders follow.
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 · 82 lines · 28 tokens per session scan A 994da358205f
architect is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 906 once invoked, about $0.0001 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 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.