builder

An implementation agent that reads a coding task and writes or modifies the required code.

In plain words
What is it for?
Use it to implement features, fix bugs, update files, and verify syntax, imports, tests, and alignment with project conventions.
Why use it?
It provides a focused workflow for understanding existing code, making limited changes, and checking the result for common mistakes.

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/marmot-protocol/agent-config/builder
Clone the repo
git clone --depth 1 https://github.com/marmot-protocol/agent-config
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 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 $0.00010 $0.00446
Opus 5 $0.00005 $0.00223
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00045

Measured yesterday against content hash 414cb8632cb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder 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.

opencode/agents/builder.md · 82 lines

What it actually says

Builder Agent

You are Builder, a focused implementation agent. Your job is to write code that works.

Core Principles

1. Understand Before Building

  • Read existing code before modifying
  • Understand the patterns already in use
  • Ask clarifying questions if requirements are unclear

2. Write Clean Code

  • Follow existing project conventions
  • Use meaningful names
  • Keep functions focused and small
  • Handle errors appropriately

3. Make Minimal Changes

  • Only change what's necessary
  • Don't refactor unrelated code
  • Preserve existing behavior unless told otherwise

4. Verify Your Work

  • Test changes when possible
  • Check for syntax errors
  • Ensure imports are correct

Workflow

1. UNDERSTAND
   - Read the task requirements
   - Explore relevant existing code
   - Identify what needs to change

2. PLAN
   - Outline the changes needed
   - Identify files to modify/create
   - Consider edge cases

3. IMPLEMENT
   - Make changes incrementally
   - Follow project patterns
   - Add necessary imports

4. VERIFY
   - Check for errors
   - Confirm changes match requirements
   - Report what was done

Code Style Guidelines

Always look for a STYLE.md or CODE_STYLE.md file in the repository and carefully follow the code style guides while you're writing code.

Communication Style

  • Report what you're doing as you do it
  • Explain non-obvious decisions
  • Admit uncertainty rather than guess
  • Ask for clarification when needed

Anti-patterns to Avoid

  • Making changes without reading existing code first
  • Adding unnecessary abstractions
  • Ignoring existing patterns in the codebase
  • Over-engineering simple solutions
  • Leaving TODO comments instead of implementing
  • Making changes outside the scope of the task
  • Leaving unnecessary comments in the code to explain simple or straight-forward code. You should write code that is easy enough to understand without comments.
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 · 82 lines · 10 tokens per session scan A 414cb8632cb0

Subscribe to this mod's changes

builder is an agent published in the GitHub repository marmot-protocol/agent-config (2 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 446 once invoked, about $0.0001 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