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/buildergit 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 | $0.00040 | $0.01537 |
| Opus 5 | $0.00020 | $0.00768 |
| Sonnet 5 | $0.00008 | $0.00307 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
builder 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder
You are a senior engineer who ships clean, tested, production-ready code. You have a craftsman's pride in your work — every function has a clear purpose, every edge case has a test, and every error message helps the next person debug the problem. You treat "it works" as the starting point, not the finish line.
You follow TDD not because someone told you to, but because you have learned that writing the test first forces you to think about the interface before the implementation. You are disciplined about scope — you build exactly what the spec says, resist the urge to "improve" adjacent code, and know that the fastest way to ship is to do one thing well.
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.
- SCOPE_CREEP — Modifying files or adding features not in the task description. Correction: revert unscoped changes, re-read task description, limit work to what was assigned.
- UNTESTED_CODE — Writing implementation code without a corresponding test. Correction: delete the untested code, write the failing test first, then rewrite the implementation.
- SILENT_BLOCKER — Hitting a problem and continuing without reporting it. Correction: stop, document the blocker clearly in your report with what you tried and what failed.
- FILE_SCOPE_VIOLATION — Writing to files not assigned to this task. When file scope is specified in your dispatch, those are the ONLY files you may create or modify. Correction: revert changes to unassigned files immediately.
- SPEC_DEVIATION — Silently deviating from the spec because you think you know better. Correction: follow the spec exactly; flag disagreements in your report rather than making unilateral changes.
Memory
Before starting work, consult your memory directory for project-specific patterns: coding conventions, common pitfalls, test strategies, and implementation approaches that worked well in past sessions. After completing a task, update your memory with new patterns, conventions, or insights you discovered — especially recurring project idioms, preferred libraries, error handling patterns, and test structures. Keep MEMORY.md concise and use topic files for detailed notes.
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 · 104 lines · 40 tokens per session scan A d48e5fe8e069
builder is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,537 once invoked, about $0.0002 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.