builder

A coding assistant that implements approved plans or clear feature requests as production code, including error handling, tests, type safety, and documentation.

In plain words
What is it for?
Use it to add features, follow an existing codebase’s patterns, write tests and documentation, and work in an isolated branch for review.
Why use it?
It turns an agreed design into working code instead of leaving scaffolds, stubs, or TODO items for someone else.

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/nxtg-ai/forge-plugin/builder
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,920 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 $0.00000 $0.01920
Opus 5 $0.00000 $0.00960
Sonnet 5 $0.00000 $0.00384
Haiku 4.5 $0.00000 $0.00192

Measured yesterday against content hash 31dea92825d0, 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.

docs/agents/builder.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Builder

The master implementer. Transforms approved plans into production-ready code with tests, type safety, and documentation — so you ship features, not TODOs.

Level L1 Vibe Coder
Category Core Workflow
Model Sonnet
Isolation Worktree (writes code in an isolated branch)

What It Does

The Builder agent is your senior engineer on demand. Give it an approved plan or a clear implementation request, and it writes the actual production code — not scaffolds, not stubs, not "TODO: implement this." Real code with real error handling, real tests, and real documentation.

What makes Builder intelligent is that it reads your codebase first. It studies your patterns, your naming conventions, your test style, your error handling approach. Then it writes code that looks like your team wrote it. The result should pass code review without anyone asking "did an AI write this?"

Builder enforces engineering standards automatically: SOLID principles, Result types for error handling, dependency injection for testability, and strict type safety. It won't let you ship code with any types, swallowed exceptions, or untested public interfaces.

When to Use It

  • After a plan is approved. You ran /forge:feature, the planner designed the architecture, you said "looks good" — now Builder implements it.
  • For focused implementation requests. "Implement a rate limiter middleware" or "Add WebSocket reconnection with exponential backoff."
  • For refactoring. "The UserService is 500 lines — break it into focused modules following SOLID."
  • When code review found quality issues. "The repository layer needs proper error handling and type annotations."

Builder is NOT for exploration or planning. If you don't know what to build yet, use the Planner first. If you want advice without changes, use the Detective in Soundboard mode.

How It Works

  1. Reads the plan. If a plan exists at .claude/plans/*.md, Builder reads it and follows the task breakdown. If invoked directly, it scopes the work from your prompt.

Read the full file on GitHub · 159 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 · 159 lines · 0 tokens per session scan A 31dea92825d0

Subscribe to this mod's changes

builder is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,920 tokens. 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.