generator-build-worker-agent

generator-build-worker-agent is an agent for Claude Code from redker56/auto-harness. It costs 23 tokens per session (257 once invoked), scanned A, original, MIT.

A worker that implements one assigned part of an Auto-Harness sprint in its own Git worktree. A worktree is a separate working copy of a Git project, allowing changes to be developed independently.

In plain words
What is it for?
It reads its assigned scope, changes only the permitted files, runs targeted checks, and commits the result for later integration.
Why use it?
It lets multiple dependency-related parts of a sprint be built separately while protecting the shared project records from accidental edits.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the auto-harness plugin — 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server shipped together

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/redker56/auto-harness/generator-build-worker-agent
Clone the repo
git clone --depth 1 https://github.com/redker56/auto-harness

Made for: Claude Code.

Or install auto-harness, the plugin that ships this one along with the rest of its 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for generator-build-worker-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/redker56/auto-harness/generator-build-worker-agent.svg)](https://agentmods.dev/agents/redker56/auto-harness/generator-build-worker-agent)
Your own site
<a href="https://agentmods.dev/agents/redker56/auto-harness/generator-build-worker-agent"><img src="https://agentmods.dev/badge/agents/redker56/auto-harness/generator-build-worker-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 257 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 5.1 $0.00023 $0.00257
Opus 5 $0.00012 $0.00129
Sonnet 5 $0.00005 $0.00051
Haiku 4.5 $0.00002 $0.00026

Measured 6d ago against content hash 15ea155dc1da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

generator-build-worker-agent 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 6d ago.

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.

agents/generator-build-worker-agent.md · 24 lines

What it actually says

You are the action-specific Generator Build Worker subagent for Auto-Harness.

You run in a fresh, isolated subagent context inside a dedicated git worktree. Your single source of behavioral truth is the preloaded generator-build-worker skill plus the specific node assignment passed in by the Orchestrator.

Runtime Contract

  • Treat the current working directory as your assigned worktree.
  • Read the local .harness-parallel/ snapshot as read-only context.
  • Implement only the assigned dependency-graph node and only inside the owned files or globs named in your assignment.
  • You may modify application source code and tests inside your owned scope.
  • You must not modify .harness-parallel/ files.
  • Run targeted verification for your node before finishing.
  • Make a local git commit in this worktree before returning.
  • In your final reply, include the commit SHA, changed files, verification run, blockers, and integration risks.
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. 6d ago First seen · 24 lines · 23 tokens per session scan A 15ea155dc1da

Subscribe to this mod's changes

generator-build-worker-agent is an agent published in the GitHub repository redker56/auto-harness (14 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 257 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 2026-08-30.