Dot Do Workers
dot-do-workers is a Claude Code plugin for the Build phase that provides three journey-wide skills for AI–human development loops spanning planning, implementation, and review.
by dot-do · github.com/dot-do/workers
Install when you want a small skill set that orchestrates brainstorm → plan → implement → review loops for AI-assisted development with humans in the loop.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install dot-do-workers@dot-do/workersBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:dot-do/workers") and the paste-ready config with skillselion.get_install_config("plugin:dot-do/workers").
What it does
dot-do-workers is a compact Claude Code plugin bundle—three skills—framed around Workers.do: combining AI, code, and human judgment into repeatable development loops. Metadata highlights brainstorming, planning, implementing, review, and continuous outer loops, including named techniques (Ralph, Wiggum) that signal iterative agent workflows rather than fire-and-forget prompts. For solo builders, this is useful whenever you need a disciplined rhythm: explore options, commit to a plan, build, then review—whether you are scoping in Validate, building features, or iterating in Operate. It is methodology and process packaging, not a hosted worker platform or CI replacement; you still run your repo, tests, and deployments. Best for developers who want Claude Code to follow explicit loop skills across the journey. Skip it if you only need a single API integration skill or fully automated unattended agents. Compared to eighty-skill marketing packs or IaC libraries, Workers is a minimal journey-wide process plugin set for agent-led product development.
Highlights
- Three Claude Code plugins embodying the Workers.do idea: AI + code + humans
- Self-referential dev lifecycle: brainstorm, planning, implementing, and review loops
- Techniques such as Ralph and Wiggum-style iterative agent work called out in metadata
- Continuous feedback loops for solo builders who treat the agent as a long-running collaborator
- Platform-oriented skills for structuring outer loops beyond one-shot codegen
Why builders use it
Solo builders lose momentum when agents produce one-off code without a repeatable brainstorm-plan-build-review loop that keeps humans steering quality and direction.
After you add the plugin, Claude Code can run structured Workers-style lifecycle skills so each feature passes through planning, implementation, and review with explicit feedback loops.
At a glance
- Type - Plugin in AI Agents.
- Adoption - 0 installs, 4 stars, 0 votes.
FAQ
Who is dot-do-workers for?
It is for solo builders and small teams who treat Claude Code as a ongoing collaborator and want explicit skills for planning, building, and review loops with humans in the loop.
When should I use dot-do-workers?
Use it at decision points across the journey—before committing to a build, while implementing, and when reviewing—whenever you want outer-loop discipline instead of ad hoc prompts.
How do I add dot-do-workers to my agent?
Install the plugin from the dot-do/workers repository in Claude Code, then invoke the Workers-related skills at the start of a task (brainstorm/plan) and again after implementation for review.
Comments
Share how you use dot-do-workers, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.