priyanshujha

Subagent Studio — Development skill for Claude Code

Development community

Claude Code plugins for running lean, single-purpose subagents: plan, build, two review passes.

How to install Subagent Studio

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

What Subagent Studio does

Claude Code plugins for running lean, single-purpose subagents: plan, build, two review passes.

Alternatives in Development

Purpose — Orient yourself in pi-vs-cc — a collection of Pi coding agent extensions and agent specs that progressively de 527 ★
Claude Code Instructions For Skills Marketplace Development — Repository: claude-skills-marketplace Purpose: Development guidelines for creating high-quality Claude Code sk 480 ★
List Tools — List all available tools as TypeScript function prototypes with parameter and purpose comments 222 ★

README

subagent-studio

A set of Claude Code plugins that turn one session into an orchestrator running lean, single-purpose subagents: plan first, build in a worktree, two review passes, enforced landing. Pulled out of a real project that ran mostly on scheduled Claude Code sessions for about five weeks.

![How a change gets made: a coordinator session, a planner, builders, two review passes and a guarded landing, with a Haiku searcher for lookups](docs/img/architecture.png)

When to use it

**Use it on medium-sized and larger codebases where changes are complex**: several files per change, real users, code you will keep for years, or scheduled runs that change things while nobody watches. That is where an independent review keeps paying. In the original project the fresh final reviewer still found a blocker or major bug in about one change in three, after the first review pass had already run.

![How often the final review found a serious bug, by change size: 9% under 50 lines, 33% at 50 to 199, 35% at 200 to 799, 38% at 800 and more](docs/img/where-it-pays.png)

**Skip it for small, well-specified work.** A single Claude Code session handles a small script or a precisely described feature in a small codebase well, at a fraction of the cost. The kit adds a planner, builders, step checks and two reviewers per change, which is several times the tokens of one session doing the same work. On a tiny change that rarely buys anything (9% in the chart above); on a real-sized one it buys a second pair of eyes that catches what the first missed.

The six ideas

**1. One agent type per role.** A builder, a reviewer, a planner and a searcher are separate agent files. Each one fixes its model, its effort level and a short tool list in its frontmatter. A reviewer gets no Edit or Write, a searcher gets four read tools. A lean type starts with a fraction of a general-purpose agent's context, and the role cannot drift into another role's job.

**2. The orchestrator never touches