urika

Agent Go — Productivity skill for Claude Code

Productivity community

Plan Mode orchestration tool — wraps Claude Code with structured Plan → Decompose → Execute workflow.

How to install Agent Go

This entry records only its repository, not the path inside it, so there is no exact command to give. Open urika/agent_go and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Go does

Plan Mode orchestration tool — wraps Claude Code with structured Plan → Decompose → Execute workflow.

Alternatives in Productivity

Epic Decompose — Break an epic into task children without creating task branches 243.5k ★
Claudekit Problem Solving — Structured problem-solving tools 1.9k ★
Pi Subagents — Claude Code like Sub-Agents & Workflow Orchestration for Pi — parallel execution, live widget, fleet view, cus 967 ★

README

agent_go

[![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-blue)](https://www.python.org/) [![Tests](https://img.shields.io/badge/tests-1864%20passed-green)](tests/) [![License](https://img.shields.io/badge/license-MIT-blue)](LICENSE) [![Stdlib Only](https://img.shields.io/badge/dependencies-stdlib%20only-brightgreen)]()

**Plan Mode orchestration tool** — wraps Claude Code with a structured `Plan -> Decompose -> Execute` workflow. LLM generates an execution plan, each step runs as an isolated subtask in its own git worktree with Claude Code. Subtasks execute concurrently with topological wave scheduling.

Why agent_go?

Give Claude Code a complex task — refactoring auth, upgrading dependencies, adding a feature — and it can drift. agent_go breaks the work into **2–5 independently executable subtasks**, each with its own isolated worktree, verification command, agent role, and skill injection. Results flow downstream via git merge.

Structured execution — LLM generates the plan, not ad-hoc decisions
Isolated worktrees — shared .git object db, each subtask on its own branch
Concurrent execution — topological wave scheduling with --parallel N
Smart role/skill routing — config-driven rules match subtasks to Agent types and Skills
Interrupt & resume — SIGINT pauses, agent_go resume picks up where you left off
Remote push — push worktree branches to a remote for CI/CD integration
Zero dependencies — pure Python stdlib
Plan cache — SHA256 cache key + 24h TTL reduces API costs
Interrupt & crash recovery — SIGINT pauses with resume; SIGKILL/abnormal exits rebuild meta.json via recover
Result review — review --task aggregates per-file diffs with approve/reject decisions; --deep adds independent-model analysis
MCP server & client — expose agent_go as an MCP server (stdio or HTTP/SSE, 6 tools); subtasks can consume tools from external MCP servers (mcp__{server}__{tool})
**