Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By nikeyes
Execute structured development workflow: research codebase with read-only agents, generate/iterate detailed implementation plans from tickets/code, implement plans with phased verification and pauses, validate via git/tests/checks, manage thoughts/ directory for notes/docs with git sync.
npx claudepluginhub nikeyes/stepwise-dev --plugin stepwise-coreCreate detailed implementation plans through interactive research and iteration
Implement technical plans from thoughts/shared/plans with verification
<!-- SPDX-License-Identifier: Apache-2.0
Document codebase as-is with thoughts directory for historical context
Validate that plan was correctly implemented, verify all success criteria
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)
Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" โ Use it if you find yourself desiring to use one of these tools more than once.
codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the location of files, it will also give you code details!
The research equivalent of codebase-analyzer. Use this subagent_type when wanting to deep dive on a research topic. Not commonly needed otherwise.
Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you can guess this is the `thoughts` equivilent of `codebase-locator`
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Corca Workflow Framework โ consolidated hooks and skill orchestration for structured development sessions
A Claude Code plugin for structured, context-efficient software development.
Plugin for effective agentic development
No description provided.
Implementation planning, execution, and PR creation workflows with multi-agent collaboration
Harness-native ECC plugin for engineering teams - 64 agents, 262 skills, 84 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Multi-agent deep research plugin with parallel web searches and synthesis
Git commit workflow without Claude attribution
Web search and research capabilities for external context
A modular development workflow suite for Claude Code inspired by Ashley Ha's workflow, adapted to work 100% locally with thoughts.
๐ Read more: Tu CLAUDE.md no funciona sin Context Engineering (Spanish article about Stepwise-dev)
Solves the context management problem: LLMs lose attention after 60% context usage.
Implements Research โ Plan โ Implement โ Validate with frequent /clear and persistent thoughts/ storage.
thoughts/This repository contains 4 independent plugins that can be installed separately based on your needs:
The foundation plugin with the complete Research โ Plan โ Implement โ Validate cycle.
Includes:
research_codebase, create_plan, iterate_plan, implement_plan, validate_plan)Clean git commit workflow without Claude attribution.
Includes:
commit)Web search and research capabilities for external context.
Includes:
web-search-researcher)Advanced multi-agent research system with parallel web searches and synthesis.
Includes:
deep_research)# Add marketplace from GitHub
/plugin marketplace add nikeyes/stepwise-dev
# Install all plugins
/plugin install stepwise-core@stepwise-dev
/plugin install stepwise-git@stepwise-dev
/plugin install stepwise-web@stepwise-dev
/plugin install stepwise-research@stepwise-dev
# Add marketplace
/plugin marketplace add nikeyes/stepwise-dev
# Install only the core workflow
/plugin install stepwise-core@stepwise-dev
# Optionally add git operations
/plugin install stepwise-git@stepwise-dev
# Optionally add web research
/plugin install stepwise-web@stepwise-dev
# Optionally add multi-agent deep research
/plugin install stepwise-research@stepwise-dev
Restart Claude Code after installation.
Don't have a project to test with? Use stepwise-todo-api-test โ a sample repository designed for testing these plugins.
After running thoughts-init (from stepwise-core) in a project:
<your-project>/
โโโ thoughts/
โ โโโ nikey_es/ # Your personal notes (you write)
โ โ โโโ tickets/ # Ticket documentation
โ โ โโโ notes/ # Personal notes
โ โโโ shared/ # Team-shared documents (Claude writes)
โ โ โโโ research/ # Research documents
โ โ โโโ plans/ # Implementation plans
โ โ โโโ prs/ # PR descriptions
โ โโโ searchable/ # Hardlinks for grep (auto-generated)
โ โโโ nikey_es/ # โ hardlinks to nikey_es/
โ โโโ shared/ # โ hardlinks to shared/
โโโ .gitignore # (add thoughts/searchable/ to this)
โโโ ...
Key distinction:
nikey_es/: Personal tickets/notes you create manuallyshared/: Formal docs Claude generates from commands/stepwise-core:research_codebase How does authentication work?
Spawns parallel agents, searches codebase and thoughts/, generates comprehensive research document.