/agent-builder

name: agent-builder
description: >
  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 itself — use guidance.
allowed-tools:
  Read, Write, Edit, Glob, Grep, Bash(find *), Bash(mkdir *),
  Bash(bash "${CLAUDE_PLUGIN_ROOT}/scripts/han-config-dir.sh")

Project Context

• personal config directory: !`bash "${CLAUDE_PLUGIN_ROOT}/scripts/han-config-dir.sh" 2>/dev/null || echo "$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 | Read | | --------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- | | Agent vs. skill vs. hook; one role (generate or evaluate) | `plugin-entity-taxonomy.md`, `agent-building-guidelines/agent-domain-focus.md` | | Domain focus, vocabulary, role identity, anti-patterns | `agent-building-guidelines/agent-domain-focus.md` | | The `description` field (four components, boundaries, length) | `agent-building-guidelines/agent-description-length.md`, `skill-building-guidance/skill-description-frontmatter.md` | | Model tier (`opus` / `sonnet` / `haiku` / `inherit`) | `agent-building-guidelines/agent-model-selection.md`, `specialization-and-model-selection.md` | | Self-containment — no references, scripts, or context injection | `agent-building-guidelines/agent-external-files.md` | | Which frontmatter fields are valid (and which plugins ignore) | `agent-building-guidelines/agent-external-files.md` | | Degraded environments (no git, missing tools) | `agent-building-guidelines/graceful-degradation.md` | | Whether this agent is justified at all; how it gets dispatched | `agent-building-guidelines/multi-agent-economics.md`, `skill-building-guidance/agent-dispatch-namespacing.md` | | New plugin needed (plugin.json, marketplace.json) | `claude-marketplace-and-plugin-configuration/` and `templates/` |

Operating Principles

• **Interview relentlessly, but explore first.** Interview the user relentlessly about every aspect of the agent until

you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. **If a question can be answered by exploring the repository — the target plugin's existing agents, sibling descriptions, the skills that would dispatch this agent, conventions, the guidance documents above — explore instead of asking.** Only surface questions that genuinely require the user's judgment.

• **Ask one question at a time.** Never batch questions. Settle one decision, let its answer resolve dependent

decisions, then ask the next. Later answers routinely make earlier questions moot.

• **Recommend, then ask.** For every question surfaced to the user, provide a recommended answer with rationale grounded

in evidence (existing agents, conventions, the guidance, the user's stated goal). The user can accept, amend, or redirect.

• **Apply guidance as you go, then verify at the end.** Consult the governing document when a decision is on the table

(Step 4), and run a full guidance-conformance pass over the finished agent at the end (Step 6). The interview gets each decision approximately right; the review pass makes the artifact correct.

• **An agent is self-contained.** Unlike a skill, an agent is a single flat `.md` file. No `references/` folder, no

`scripts/` folder, no `` !`command` `` context injection. Everything the agent needs is inlined in its body.

Build an Agent

Step 1: Capture the Request and Confirm It Is an Agent

Read the user's argument and the conversation to extract what the agent should do. If the request is too thin to start (for example, just "build an agent"), ask the user for one or two sentences on the agent's domain and what it produces — nothing else y