Command Creator

Create Claude Code commands — user-invocable workflows that orchestrate agents, interview users, and delegate complex work through structured phases.

Core Process

1. Classify Command Scope

Determine structure before drafting:

• How many phases? Simple commands (1-2 phases) vs orchestration commands (5+ phases).
• Does the command need subagents, or can it run entirely in the main context with Read/Glob/Grep/Bash? Default to main context; only add Agent delegation when the work must run in a fresh context or with a different model.
• Interactive (AskUserQuestion gates) or autonomous (runs end-to-end without prompts)?
• What approval gates are needed before destructive or irreversible actions?

2. Research Existing Commands

Use Glob + Read directly to find similar commands in the target project:

• Glob **/commands/*.md, read 2-3 representative files
• Note phase structure, frontmatter fields, and whether they use subagents or direct tools

3. Dedup Audit

Read ${CLAUDE_SKILL_DIR}/../prompt-writer/references/cc-dedup-guide.md before drafting.

Key dedup rules for commands:

• Commands receive CLAUDE.md automatically — do not re-state its global directives.
• Do not repeat Intent Gate, Delegation Check, or barrier semantics — these load every message.
• Do not re-explain agent model routing rules already in global CLAUDE.md.
• Commands specify WHAT to do (which agents, which phases) not HOW CC should behave.

4. Draft Command

Follow phase-based structure from references/command-patterns.md. Each phase uses:

## Phase N: Name

**Goal**: One sentence — what this phase achieves.

**Actions**:

1. First action
2. Second action
3. Third action (with sub-steps if needed)

Rules:

• Phases must be sequential — later phases depend on earlier ones.
• Insert AskUserQuestion approval gates before destructive actions.
• Delegate heavy work to agents — commands orchestrate, agents execute.
• Reference $ARGUMENTS for user-supplied input.
• Use ${CLAUDE_PLUGIN_ROOT} for paths to bundled templates.

5. Frontmatter

---
description: "Short, action-oriented. What does this command do? ≤250 chars."
argument-hint: "[expected-input]"
effort: low | medium | high
---

Notes:

• Do not declare allowed-tools, disallowedTools, or model. CC ignores them at runtime for user-level plugin components; tool access flows from session permissions.
• Always include AskUserQuestion and Agent if the command interviews users or delegates to agents.
• effort signals expected token budget: low (single task, <5 phases), medium (multi-agent, 5-7 phases), high (full orchestration, 7+ phases).
• Do not add model to command frontmatter — commands inherit the session model. Only agents have model routing.

6. Review

Present draft. Verify before finalizing:

• Phases sequential? No phase assumes work from a later phase.
• Approval gates present before destructive or irreversible actions?
• Agent delegation clear? Each Agent call has TASK + EXPECTED OUTCOME + MUST DO + MUST NOT DO + CONTEXT.
• Error handling covers: missing input, agent failure, no changes found, user cancellation.
• $ARGUMENTS referenced at the right phase (usually Phase 1)?
• No ineffective frontmatter declared (model, allowed-tools, disallowedTools)?

Agent Delegation Patterns

Parallel Foreground (wait for all)

All agents in a single message block — CC waits automatically:

Agent(subagent_type: "<your-search-agent>", prompt: "...")
Agent(subagent_type: "<your-analysis-agent>", prompt: "...")

Use when results are needed before proceeding. Do NOT advance to the next phase until all agents complete.

Background (genuinely independent work)

Agent(subagent_type: "<your-worker>", run_in_background: true, prompt: "...")
Agent(subagent_type: "<your-worker>", run_in_background: true, prompt: "...")

Use only when you have independent work to continue while agents run. Collect all completion notifications before the next phase.

Model Routing per Agent

Pass model: to override per agent — do not upgrade all agents to Opus:

Agent Prompt Template

Every agent delegation follows this structure:

TASK: [What the agent must accomplish — one clear sentence]

EXPECTED OUTCOME: [What the agent returns — file:line refs, verdict, structured output]

MUST DO:
- [Specific constraint 1]
- [Specific constraint 2]

MUST NOT DO:
- [What to exclude or avoid]

CONTEXT: [Relevant state — plan path, conventions, prior findings]

String Substitutions

Variables available in command bodies (replaced at load time by CC):

Use ${CLAUDE_PLUGIN_ROOT} to reference bundled templates:

Read template from `${CLAUDE_PLUGIN_ROOT}/references/my-template.md`

References