agent-builder
Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the agent's design tree decision-by-decision — entity fit, domain focus and vocabulary, role identity, anti-patterns, description, model tier, tools, and self-containment — then reviews the finished agent against the plugin-building guidance and applies every fix it finds. Use when creating, authoring, scaffolding, designing, or drafting a new agent or subagent. Does not build a skill or slash command — use skill-builder. Does not serve, vendor, or refresh the authoring guidance its
npx skills add testdouble/han --skill agent-builder --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Project Context - personal config directory: !`echo "${CLAUDE_CONFIG_DIR:-$HOME/.claude}"` - project .han/config.md: !`cat .han/config.md 2>/dev/null || echo ""` As your first action, use the Read tool on `.han/config.md` inside the `personal config directory` path above. A read that returns no file is no personal configuration: continue silently. When that file or the `project .han/config.md` probe supplies content, apply it per [config-rule.md](../../references/config-rule.md), which governs precedence between the two files, relative-path resolution, and what to do with a file that reads but cannot be used. ## Guidance Location The authoritative agent-authoring guidance ships in this plugin. Read the specific document a decision needs, when that decision is on the table — never read them all up front, because that defeats progressive disclosure and burns context on guidance the current agent does not touch. - Plugin-building guidance root: `${CLAUDE_PLUGIN_ROOT}/skills/guidance/references/` - Agent-specific guidance: `${CLAUDE_PLUGIN_ROOT}/skills/guidance/references/agent-building-guidelines/` Map from decision to governing document (read just-in-time): | Decision on the table
- Project Context
- Guidance Location
- Operating Principles
- Step 1: Capture the Request and Confirm It Is an Agent
- Step 2: Discover Before Asking
- Step 3: Build the Design Tree
- Step 4: Interview Loop — One Branch at a Time
- Step 5: Write the Agent
- Step 6: Full Guidance-Conformance Review
- Step 7: Present and Hand Off
What does the agent-builder skill do?
Builds a new Claude Code agent (subagent) from scratch through a relentless, evidence-based interview that walks the agent's design tree decision-by-decision — entity fit, domain focus and vocabulary, role identity, anti-patterns, description, model tier, tools, and self-containment — then reviews the finished agent against the plugin-building guidance and applies every fix it finds. Use when creating, authoring, scaffolding, designing, or drafting a new agent or subagent. Does not build a skill or slash command — use skill-builder. Does not serve, vendor, or refresh the authoring guidance its
How do I install it?
Run `npx skills add testdouble/han --skill agent-builder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From testdouble/han, a repository with 154 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.