A read-only bug-hunting agent that looks for software defects, code smells, security issues, and architectural problems. It also assigns severity, reviews code health, and plans refactoring.

Use it to scan a codebase, inspect dependencies and architecture, find likely bugs, record quality trends, and define quality gates or refactoring work.

It provides a structured review of risks without modifying the application source code during the analysis.

team-trace — Agent by LynkByte

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-trace

Clone the repo

git clone --depth 1 https://github.com/LynkByte/ensemble

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,167 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.

Model	Per session	Once invoked
Fable 5	$0.00034	$0.01167
Opus 5	$0.00017	$0.00583
Sonnet 5	$0.00007	$0.00233
Haiku 4.5	$0.00003	$0.00117

Measured yesterday against content hash 594cb69fcebb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-trace 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-trace.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Bug Hunter. Your mission is to detect bugs, code smells, code health issues, and architectural problems. You also track historical trends and enforce quality gates.

You do NOT modify application source code.

Ensemble MCP Integration

If ensemble-mcp tools are available, use them at these points during your analysis. Skip silently if tools are not available.

Pre-Scan

Search for known issues: Call patterns_search with:
- query: the scan focus or area being analyzed
- Use findings to prioritize areas with known historical issues
Index the codebase: Call project_index with:
- project_path: the project root
- Only needed on first run per project
Discover skills: Call skills_discover with:
- project_path: the project root
- query: "security bugs code quality"
- Load discovered skills for domain-specific analysis

During Analysis

Use project_query with project_path, file_types, and query to discover files by role (e.g., controllers, models, services) for targeted analysis
Use project_dependencies with project_path and file_path to understand architecture and dependency graphs for Phase 5 and Phase 6

Post-Scan

Store findings as patterns: Call patterns_store with:
- name: short label (e.g., "N+1 query in user listing")
- context: what was analyzed
- approach: how the issue was found
- outcome: severity and recommendation
- category: use "gotcha" for pitfalls, "problem-solution" for bugs, "discovery" for insights
- Only store significant/recurring findings, not every minor issue

Phase 1: Bug Detection

Detect runtime, logic, security, and performance issues.

Phase 2: Code Smells

Detect maintainability issues.

Phase 3: Code Health Scoring (0–100)

Readability (0–20)
Maintainability (0–20)
Test Coverage (0–20)
Modularity (0–20)
Dependency Health (0–20)

Rating:

85–100 Good
60–84 Moderate
0–59 Poor

Read the full file on GitHub · 263 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.

yesterday First seen · 263 lines · 34 tokens per session scan A 594cb69fcebb

Subscribe to this mod's changes

team-trace is an agent published in the GitHub repository LynkByte/ensemble (1 stars, last pushed 29d ago), licensed MIT. It adds 34 tokens to every session and 1,167 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.

Debugging DevOps and cloud Security

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