Stroi Planner — Development agent for Claude Code
Use this agent when a goal needs expanding into a concrete, file-level plan before any code is written.
How to install Stroi Planner
Installs to ~/.claude/agents/stroi-stroi-stroi-planner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Stroi/stroi/HEAD/agents/stroi-planner.md -o ~/.claude/agents/stroi-stroi-stroi-planner.md Restart Claude Code, or start a new session, for it to be picked up.
What Stroi Planner does
name: stroi-planner description: Use this agent when a goal needs expanding into a concrete, file-level plan before any code is written. Typical triggers include designing a plan-big run from a goal plus exploration findings, and re-planning a checkpoint after a failed verify gate. Researches current library docs before designing against any API and returns the plan as text for the orchestrator to present; does not implement it. model: inherit color: magenta effort: high
You are **stroi
Alternatives in Development
- Tech Stack Researcher — Use this agent when the user is planning new features or functionality and needs guidance on technology choice 1.5k ★
- General PM — Use this agent proactively when you need comprehensive product management oversight for software development i 248 ★
- Standards Reviewer — 工程规则专项审查。仅根据项目明确的编码规范、目录/分层约束、宏/日志/include 规则和成熟库复用要求，识别违反工程规则的问题 104 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Stroi Developer
Use this agent when an approved stroi plan needs its code actually written. Typical triggers include building
Stroi Scribe
Use this agent when rote text needs writing cheaply and no judgment is required. Typical triggers include draf
Privesc Agent
Use this agent when there's an initial low-privilege shell on an authorized lab target and privilege escalatio
Proj Work
Use this agent when creating or executing work items during automated development cycles. Typical triggers inc
Wiki Adapter PRD
Use this agent when mapping foreign PRD formats into vault pages during automated processing cycles. Typical t
Exploit Agent
Use this agent when a recon findings file already exists for a target and an initial-access foothold needs ide
Related Skills
Six
Use this skill to run test coverage analysis and write tests for uncovered code. Run it when asked to improve
Learning Goal
A Claude Code skill for designing learning goals during AI-assisted coding
Tilth
A local-first garden almanac & planner — but really an experiment in agent-first, no-hand-coding development:
