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.
npx agentmods add agents/nxtg-ai/forge-plugin/buildergit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01920 |
| Opus 5 | $0.00000 | $0.00960 |
| Sonnet 5 | $0.00000 | $0.00384 |
| Haiku 4.5 | $0.00000 | $0.00192 |
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.
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
- 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.
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 · 159 lines · 0 tokens per session scan A 31dea92825d0
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.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.