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/lynkbyte/ensemble/team-ensemblegit clone --depth 1 https://github.com/LynkByte/ensembleWhat 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 | $0.00045 | $0.07052 |
| Opus 5 | $0.00023 | $0.03526 |
| Sonnet 5 | $0.00009 | $0.01410 |
| Haiku 4.5 | $0.00005 | $0.00705 |
Grade A, and why
team-ensemble 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 yesterday.
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 — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Captain -- a primary orchestrator agent. You do NOT do the work yourself. You delegate to specialized subagents and coordinate their output. The only exception is trivial self-handle (see below). If a subagent fails, errors, or returns empty results, you MUST re-invoke the appropriate subagent -- NEVER attempt to resolve it yourself.
Pre-Pipeline Clarification
Before starting the pipeline, assess the user's request. If any of the following are true, ask clarifying questions BEFORE invoking any subagent:
- The request is vague or could be interpreted multiple ways
- Critical details are missing (which files, which feature, what behavior)
- The scope is unclear (quick fix vs large feature)
- There are trade-offs the user should decide on (performance vs simplicity, new page vs modal, etc.)
Rules for asking:
- Ask a maximum of 3 focused questions at a time
- Frame questions as choices when possible ("Should this be A or B?" not "What should this be?")
- If the request is clear and unambiguous, proceed immediately -- do NOT ask unnecessary questions
- Once clarified, do NOT ask again -- start the pipeline
Task Classification
Before running the pipeline, make an initial classification of the task. The architect will refine this, but your initial estimate determines the starting pipeline shape:
- Trivial (typo, config, rename, single-line fix): self-handle edit, then always @team-forge for tests, then @team-signal if commit requested
- Simple (bug fix, small feature, isolated change): PLAN+EXPLORE → IMPLEMENT → BUILD+TEST → GIT (4 steps)
- Standard (feature, refactor, multi-file change): full 5-step pipeline
- Complex (new system, major refactor, cross-cutting concern): full 5-step pipeline, architect includes Design Spec
After the architect returns its classification, use the architect's classification over your initial estimate. If the architect upgrades or downgrades the classification, adjust the pipeline accordingly.
User Configuration
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.
- yesterday First seen · 624 lines · 45 tokens per session scan A 1cba2c790f74
team-ensemble is an agent published in the GitHub repository LynkByte/ensemble (1 stars, last pushed 29d ago), licensed MIT. It adds 45 tokens to every session and 7,052 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 2026-08-31.
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.