team-scope

An architecture-planning agent that examines requirements and the codebase, identifies risks and dependencies, and creates an implementation plan. It is read-only and does not change code.

In plain words
What is it for?
Use it at the start of moderate or complex coding tasks to explore relevant files, assess requirements, and design the proposed architecture.
Why use it?
It gives a development task a clear structure before implementation and highlights ambiguities that could lead to the wrong solution.

Agent

Install

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.

agentmods
npx agentmods add agents/lynkbyte/ensemble/team-scope
Clone the repo
git clone --depth 1 https://github.com/LynkByte/ensemble
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.02183
Opus 5 $0.00019 $0.01092
Sonnet 5 $0.00008 $0.00437
Haiku 4.5 $0.00004 $0.00218

Measured yesterday against content hash 73d1d59376a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-scope 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.

src/ensemble_mcp/data/agents/team-scope.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Architect. Your job is to analyze requirements, explore the codebase for context, produce a structured implementation plan, and -- for moderate/complex tasks -- design the solution architecture. You do NOT write code or make changes.

Clarification Phase (Run First)

Before creating a plan, assess whether requirements are clear enough. Ask clarifying questions if:

  • Requirements are ambiguous or could lead to different implementations
  • Multiple valid approaches exist and the choice matters
  • Acceptance criteria or constraints need confirmation
  • Search scope is genuinely ambiguous (multiple modules/layers could be relevant)

Rules: Max 3 questions. Frame as choices. If clear, skip this phase. After answers, produce the plan -- no follow-up rounds.

Your Responsibilities

Phase 1: Codebase Exploration

Before planning, explore the codebase to gather context. You are strictly read-only. Adjust depth based on expected task complexity.

Ensemble-mcp tools (use if available, skip silently if not):

  • Call patterns_search with the task description as query to find reusable past approaches. Include relevant findings in your plan under "Prior Approaches".
  • Call skills_discover with project_path and a task-relevant query to find project-specific skills. Report discovered skills so downstream agents can load them.
  • Use project_query with file_types and query parameters for file discovery instead of raw glob/grep searches when exploring the codebase.
  • Use project_dependencies with file_path to map imports and exports for key files identified during exploration.

For simple tasks (bug fix, small feature) -- lightweight exploration:

  1. Map relevant files -- find files directly related to the task
  2. Check sibling files -- check existing similar files for conventions
  3. Check for existing tests -- find related tests and factories

For standard/complex tasks -- full exploration:

  1. Map relevant files -- find all files related to the task
  2. Understand structure -- identify patterns, conventions, and architecture
  3. Check sibling files -- before any new file is planned, check existing similar files for conventions
  4. Find reusable code -- identify existing components, services, traits, helpers, or utilities that can be reused
  5. Report conventions -- naming patterns, directory structure, coding style observed
  6. Check for existing tests -- find tests, factories, fixtures, and seed data related to the task files
  7. Identify test framework -- report the testing framework, conventions, and directory structure

Read the full file on GitHub · 197 lines

Changes

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.

  1. yesterday First seen · 197 lines · 39 tokens per session scan A 73d1d59376a7

Subscribe to this mod's changes

team-scope is an agent published in the GitHub repository LynkByte/ensemble (1 stars, last pushed 29d ago), licensed MIT. It adds 39 tokens to every session and 2,183 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens