Han is a suite of AI skills and agents for solo (or small-team) product engineers. It combines evidence-based planning, test-driven implementation, full documentation maintenance, deep code review, and architectural analysis into a team of specialists you can dispatch from Claude Code.
Han turns planning, implementation, review, and documentation work that would normally take a team into a set of deterministic skills you run from Claude Code. Each skill dispatches specialist agents (project managers, adversarial reviewers, investigators, architectural analysts, testing and security specialists) to do the judgment-heavy work, then folds their findings into an artifact you can trust.
The skills are designed to compose. You can plan a feature, then plan its implementation, then iterate on the plan, then build it test-first, then review the resulting code, then write the PR description. All through named skills that hand off to each other cleanly.
Read Concepts for the skill-and-agent model that runs through the whole plugin.
Evaluating Han for a larger org? Han is built for solo product engineers and small teams, not for large teams or enterprise. Read Why solo and small teams, and not large teams or enterprise? for the honest fit answer before going further.
- New to han? → Start with Concepts, then the Quickstart.
- Deciding which plugin to install? → Choosing a Han plugin. The bundled suite, core only, the opt-in
han.feedbackplugin, and the dependency that surprises people, with a quick "which one do you need?" guide.
- Want the end-to-end recipe for a workflow? → How-to guides. Plan a feature, triage and investigate a bug, or research a decision, walked through step by step.
- Want to send the maintainers feedback? → How to provide feedback on Han. Shape an idea or complaint into a postable issue with
/issue-triage, or summarize a session with the opt-inhan.feedbackplugin.
- Looking for a specific skill? → Skills Index. All skills grouped by purpose.
- Looking for a specific agent? → Agents Index. All agents grouped by role.
- Wondering how the agent swarms scale? → Sizing. The small / medium / large dispatch model used by
/architectural-analysis,/code-review,/gap-analysis,/iterative-plan-review,/plan-a-feature,/plan-implementation, and/research. - Wondering why a skill said "YAGNI"? → YAGNI. The evidence-based rule every planning, review, and architecture skill applies before committing items to an artifact.
- Wondering what counts as evidence? → Evidence. The three principles (proximity, corroboration, no-evidence labeling) and the trust-class vocabulary every evidence-aware skill and agent applies.
- Want to extend Han with custom skills? → Extend Han with plugin dependencies explains how one plugin builds on another through the
dependenciesfield, using Han's own multi-plugin split as the worked example. Build a plugin that depends on Han is the hands-on walkthrough: stand up your own plugin, add a skill that builds onhan.core, and confirm a clean install pulls Han in alongside it. - Writing or editing a skill or agent? → Contributing.
Add the Test Double skills marketplace to Claude Code, then install the plugin:
/plugin marketplace add testdouble/han
/plugin install han@han
Han ships as five plugins:
han: a meta-plugin with no components of its own that depends onhan.core,han.github, andhan.reportinghan.core: the planning, investigation, review, and documentation skills plus every agenthan.github: GitHub-facing skills like posting a code review on a PRhan.reporting: reporting skills like the stakeholder summaryhan.feedback: an opt-in skill for capturing post-session feedback on Han skill runs
Installing han@han pulls in the bundled suite (the meta-plugin plus han.core, han.github, and han.reporting),
and is the right choice for almost everyone. If you do not want the GitHub or reporting skills, install han.core@han
instead. There is no GitHub-only or reporting-only install: both han.github and han.reporting depend on han.core,
so installing either brings the core skills and every agent along with it. han.feedback is the exception: it depends
on han.core too, but the han meta-plugin does not pull it in, so install it separately with han.feedback@han if
you want it.
For the full picture and a quick "which one do you need?" guide, see Choosing a Han plugin.
- Concepts. Skill vs. agent, and how they compose. Read once before using the plugin.
- Choosing a Han plugin. The full suite vs. core only, the
han.githubandhan.reportingdependencies onhan.core, and a quick guide to which one to install. - Quickstart. Five paths for five common situations. Each path is a short sequence of skills.
- How-to guides. End-to-end recipes for planning a feature, triaging and investigating a bug, and researching a decision. Pick one when you want the full walkthrough, not only the path.
- Skills Index. All skills, grouped by purpose.
- Agents Index. All agents, grouped by role.
- Sizing. The small / medium / large model that decides how many agents the swarming skills dispatch.
- YAGNI. The evidence-based "You Aren't Gonna Need It" rule every planning, review, and architecture skill applies.
- Evidence. What counts as evidence in Han, how to characterize how strong it is, and what to do when no evidence exists at all.
- Contributing. Adding or editing skills, agents, and documentation.
- Changelog. What's new in each version of the plugin.
- Maintenance horizon: Indefinitely maintained, best-effort. No SLA.
- Project type: Personal project, with some Test Double support
- How to report issues: GitHub Issues, with expected best effort for response within 2 weeks.
Han is an open source product of Test Double, and maintained by the following people:
- River Lynn Bailey: Creator, and primary maintainer
Copyright 2026 Test Double, Inc. Distributed under the MIT license.