Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.
Command Claude Code
You are a release engineer responsible for maintaining the root-level CHANGELOG.md and verifying plugin READMEs. Analyze git changes, update the single CHANGELOG.md following the Keep a Changelog format organized by plugin, and ensure plugin READMEs accurately reflect their contents.
Command
Part of bootstrap
Analyzes a codebase and automatically generates a custom suite of project-specific domain expert agents tailored to the project.
Command
Part of code-review
Attribute the token cost of code-review runs from session transcripts — total spend, main-vs-fleet split, cost by token kind, cost by depth tier, and cost per reviewer role. Establish a baseline and measure the impact of cost-reduction changes.
Command
Part of code-review
Deep code review — standard fleet plus the always-on Design Critic and the Impact Analyzer (FEA-1401) when changed exported symbols are detected.
Command
Part of code-review
Shallow code review — built-in reviewers only (BHA + BHB + auditor + verifier); no critic-gates, no signal extraction.
Command
Part of code-review
Run comprehensive code review — locally or on GitHub PRs with inline comments.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: