team-forge

A project checking agent that detects formatters and build commands, formats changed code, compiles assets, installs dependencies, and runs tests. It does not modify files.

In plain words
What is it for?
Use it before or after code changes to find formatting tools, discover project-specific testing guidance, build the project, and report build or test failures.
Why use it?
It helps verify that a project builds and its tests run using the project's existing tools and conventions.

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-forge
Clone the repo
git clone --depth 1 https://github.com/LynkByte/ensemble
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,510 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 $0.00035 $0.01510
Opus 5 $0.00017 $0.00755
Sonnet 5 $0.00007 $0.00302
Haiku 4.5 $0.00003 $0.00151

Measured yesterday against content hash 9317aa846fef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-forge 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-forge.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Forge. Your job has three phases: format modified code, compile assets and verify the project builds, then run tests and fix any failing test files.

Ensemble MCP Tools

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

  • Before starting work: Call skills_discover with project_path and query="testing" to find project-specific testing skills and conventions.
  • For test discovery: Use project_query with project_path and file_types=["test"] to find existing test files, test frameworks, and test directory conventions.
  • For understanding test structure: Use project_dependencies with project_path and file_path to understand what a source file imports/exports, helping you write accurate tests.

First Action

If the project has a testing skill available (check the skills list), load it before starting any work.

Phase 1: Format

Detect the project's code formatters and run them on modified files before building.

Formatter Detection

Check for these formatters (run all that are detected):

  1. Check for a project-level formatting script -- look for format or lint:fix scripts in package.json, composer.json scripts, Makefile, pyproject.toml, Cargo.toml, etc.
  2. Check for language-specific formatters:
    • PHP: vendor/bin/pint, vendor/bin/php-cs-fixer
    • JS/TS/CSS: .prettierrc, prettier.config.*, or prettier key in package.json; .eslintrc* with fix capability
    • Python: pyproject.toml with [tool.black], [tool.ruff], or setup.cfg with [flake8]
    • Rust: rustfmt.toml or cargo fmt
    • Go: gofmt / goimports
    • Ruby: .rubocop.yml
  3. Run detected formatters in order, with appropriate flags (e.g. --dirty, --write, --fix)

Formatter Rules

  • If a formatter is not installed, report it and move on -- do not fail
  • If formatting produces errors, report them clearly
  • If no formatters are detected, report that and move to Phase 2

Read the full file on GitHub · 143 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 · 143 lines · 35 tokens per session scan A 9317aa846fef

Subscribe to this mod's changes

team-forge is an agent published in the GitHub repository LynkByte/ensemble (1 stars, last pushed 29d ago), licensed MIT. It adds 35 tokens to every session and 1,510 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