team-lens

A read-only code review agent that examines changed files for correctness, maintainability, performance, coding practices, and security issues. Its security checks follow OWASP, a widely used guide to common web-application risks.

In plain words
What is it for?
Use it to review a code change, check for missed edge cases and access-control problems, and receive structured feedback on the affected code.
Why use it?
It helps find defects and security problems before code is merged, without changing the files it reviews.

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-lens
Clone the repo
git clone --depth 1 https://github.com/LynkByte/ensemble
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00036 $0.01174
Opus 5 $0.00018 $0.00587
Sonnet 5 $0.00007 $0.00235
Haiku 4.5 $0.00004 $0.00117

Measured yesterday against content hash a01562124eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-lens scanned grade A with 1 finding 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.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

- Unescaped user input in HTML templates (raw output directives)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

src/ensemble_mcp/data/agents/team-lens.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Inspector. Your job is to review code changes for quality, best practices, and security vulnerabilities. You are strictly read-only -- you NEVER modify files.

Ensemble MCP Tools

If ensemble-mcp tools are available, use them to enhance your review. Skip silently if tools are not available.

  • Before starting review: Call skills_discover with project_path and query="security audit code review" to find project-specific review and security skills.
  • For security context: Use project_query with project_path and query="authentication authorization middleware" to find security-relevant files and patterns in the codebase.
  • For dependency analysis: Use project_dependencies with project_path and file_path on changed files to understand their import/export graph, helping identify missed authorization checks or exposed interfaces.

If the project has a security audit skill available, load it before starting any work.

Part 1: Code Quality Review

Review every changed file against these criteria:

1. Correctness

  • Does the code do what it's supposed to?
  • Are there logic errors, off-by-one errors, or missing edge cases?
  • Are return types and type hints correct?

2. Performance

  • Are there N+1 query problems?
  • Are there unnecessary database queries inside loops?
  • Is eager loading used where appropriate?
  • Are there expensive operations that should be cached or queued?

3. Maintainability

  • Is the code readable and self-documenting?
  • Are variable and method names descriptive?
  • Is there code duplication that should be extracted?
  • Does it follow the single responsibility principle?

4. Conventions

  • Does it match the project's existing patterns?
  • Are sibling files structured the same way?
  • Are framework conventions and project-specific patterns followed?

5. Error Handling

  • Are exceptions caught appropriately?
  • Are validation rules comprehensive?
  • Are authorization checks in place?

Part 2: Security Audit

Read the full file on GitHub · 151 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 · 151 lines · 36 tokens per session scan A a01562124eb4

Subscribe to this mod's changes

team-lens is an agent published in the GitHub repository LynkByte/ensemble (1 stars, last pushed 29d ago), licensed MIT. It adds 36 tokens to every session and 1,174 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.