Harness Shipper — Development agent for Claude Code
Fresh shipping agent for goal loops.
How to install Harness Shipper
Installs to ~/.claude/agents/leadgrowgtm-loop-engineer-harness-shipper.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/LeadGrowGTM/loop-engineer/HEAD/.claude/agents/harness-shipper.md -o ~/.claude/agents/leadgrowgtm-loop-engineer-harness-shipper.md Restart Claude Code, or start a new session, for it to be picked up.
What Harness Shipper does
name: harness-shipper description: Fresh shipping agent for goal loops. Runs the no-mistakes validation pipeline exactly once after Checker PASS, drives gates to a terminal outcome, and returns the PR URL and fixes. Never runs for ITERATE or PLATEAU. tools: Read, Bash model: claude-sonnet-5
You are the Harness Shipper. You are a fresh agent spawned only after the Harness Checker returns PASS. You did not make or score the change.
Input
- Absolute RUN.json path and recorded run path
Alternatives in Development
- Oh My Pi — AI coding agent for terminal with hash-anchored edits, LSP, subagents and more 2k ★
- Agent Of Empires — Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI Coding Agent Terminal Session manager via tmux and 1.2k ★
- Agent Refactorer — Principal Clean Code Specialist specializing in code simplification, performance tuning, and refactoring loops 957 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Harness Prover
Running-app verifier for harness eval loops. Drives the live feature (browser, API, or CLI) and returns a bina
Org Verifier
Independently verifies that a change does what its author claims — reruns the repository gate, exercises CLIs,
Run Issues Finale
Coherence finale for a /run-issues run — reviews the entire branch diff as one change, drives cross-issue seam
Sdlc Coder
Drives strict TDD (Red→Green→Refactor) implementation of one story file, in the target repository. Always load
Staging E2e Verifier
Use this agent to execute the approved plan's E2E scenarios against a staging URL via Playwright MCP. It runs
Browser Checker
Opens a URL, checks a short written list of things, and reports what it saw in a paragraph. Keeps screenshots
Related Skills
Loopgen Rs
Agentic loop runner for Claude Code — turns a goal into an iterative claude -p loop with a LOOP_STATUS termina
Product Mode
The most expensive bug in AI-assisted building is shipping the wrong thing, well. A CLAUDE.md for PM + eng tea
AI Answer Fact Checker
Claude Code skill that lists the claims in an AI answer that could be wrong, rates each one's risk, and says e