subagent

voidbeast-gpt41enhanced — Claude Code subagent: modes and install

Q: How do I install voidbeast-gpt41enhanced in Claude?

Run `npx claude-code-templates@latest --agent expert-advisors/voidbeast-gpt41enhanced`, then confirm the file landed at `.claude/agents/voidbeast-gpt41enhanced.md`.

Q: What does prompt generator mode need to work?

Internet access. The subagent uses `fetch` and `openSimpleBrowser` to verify current practices and libraries before writing a prompt.

An autonomous full-stack subagent that picks its own mode, digs through the codebase and keeps working until the problem is solved.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --agent expert-advisors/voidbeast-gpt41enhanced

Open on GitHub

What voidbeast-gpt41enhanced does

voidbeast-gpt41enhanced is a Claude subagent built to act as an autonomous developer. It reads your phrasing and switches modes on its own: planning, acting, deep research, analysis, checkpoints and prompt generation. In prompt generator mode it refuses to write code right away, gathering web sources first and producing a detailed prompt.md.

Behaviour is governed by a set of operating rules. After every file edit the subagent must review the code for syntax errors, duplicates and orphaned elements, then check the result against the requirements. Analyzer mode scans architecture, dependencies and security, sorts findings into critical, important and optimization buckets, and waits for your approval before touching anything. Checkpoints go to the /memory/ directory, also after confirmation.

One thing to know upfront: prompt generator mode treats its own knowledge as outdated and insists on internet research through fetch and openSimpleBrowser. Without network access that path will not run.

What it helps with

map an unfamiliar codebase and understand its architecture
plan a migration or large refactor before writing code
spot performance bottlenecks and technical debt
check recent edits for duplicates and broken elements
research libraries and get a ready-to-use prompt

Example prompts for the agent

analyze this project and draft a migration plan for the new framework version
create a checkpoint of the project and save the report to memory
run deep research on which form library to use

How to install voidbeast-gpt41enhanced

1claude-code-templates

npx claude-code-templates@latest --agent expert-advisors/voidbeast-gpt41enhanced

2Manually: put the files in place

.claude/agents/voidbeast-gpt41enhanced.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Manually: put the files in place

.codex/agents/voidbeast-gpt41enhanced.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Manually: put the files in place

.cursor/agents/voidbeast-gpt41enhanced.md

Cursor also reads .claude/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

From the same set205

The whole set →

code-permutation-tester Runs several implementation approaches through simulation and scored quality gates so you pick one before writing the real code. 184installs digital-twin-creator Walks the agent through mapping, calibration and scenario testing to produce a digital twin of a process or system. 176installs pac-configure Sets up a Product as Code structure: .pac/ directory, config, epic and ticket templates. Useful when product work lives in the same repo as code. 176installs add-mutation-testing A slash command that sets up mutation testing in your project: picks a framework, wires quality thresholds and hooks the run into CI. 172installs backend-to-frontend-handoff-docs Turns finished backend work into a handoff document for frontend developers: endpoints, DTOs, validation and edge cases in one markdown file. 164installs change-logger This hook writes each file mutation to a CSV: timestamp, tool, path, action and details. Handy when you are prepping a demo and need to show what the agent touched. 163installs git-bisect-helper Runs a git bisect session and marks commits good or bad from your test's exit code. Useful when you know something broke but not where. 163installs cloud-architect A Claude skill for designing infrastructure across AWS, Azure and GCP, with Terraform, CDK, cost work and security controls. 157installs

Nearby in Agent setup: memory, context, orchestration

All subagents for Agent setup: memory, context, orchestration →

Questions about voidbeast-gpt41enhanced

How do I install voidbeast-gpt41enhanced in Claude?

Run npx claude-code-templates@latest --agent expert-advisors/voidbeast-gpt41enhanced, then confirm the file landed at .claude/agents/voidbeast-gpt41enhanced.md.

What does voidbeast-gpt41enhanced do?

It is an autonomous full-stack subagent. It detects its own mode, plans, analyzes code, keeps checkpoints and generates prompts backed by web research.

What does prompt generator mode need to work?

Internet access. The subagent uses fetch and openSimpleBrowser to verify current practices and libraries before writing a prompt.