Command
Agent Orchestration
Command
/agent
--- description: Force usage of a specific agent argument-hint: <agent-name> ---
Install
$ npx -y skills add Aedelon/claude-code-blueprint --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/agent
Context preview
What this command does when you run it.
--- description: Force usage of a specific agent argument-hint: <agent-name> ---
Command definition
agent.md--- description: Force usage of a specific agent argument-hint: <agent-name> ---
Agent Selection Override
You MUST now adopt the role and instructions of the agent: **$ARGUMENTS**
Available Agents
| Name | Domain | Description | |-----|---------|-------------| | `research-synthesizer` | Research | Multi-source academic synthesis | | `midjourney-expert` | Creative | Midjourney V7, Niji, prompts, moderation | | `prompt-engineer` | Meta | LLM prompt engineering | | `finance-advisor` | Finance | Investment, crypto, budgeting |
Instructions
1. Read the corresponding agent file in `~/.claude/agents/[name].md` 2. Fully adopt its role, tone, and methodology 3. Apply its specific rules for all subsequent responses 4. Confirm activation with: "Agent **[name]** activated."
If the Agent Doesn't Exist
List available agents and ask the user to choose.
Rules
- The agent remains active until explicit change
- Apply all agent rules (web search, citations, etc.)
- Combine with global rules from CLAUDE.md
Ships withclaude-code-blueprint
A production-grade Claude Code configuration: skills, agents, hooks, rules, and permissions working as a system, not as isolated features. Companion repo for the article: "I Turned Claude Code Into an Operating System. Here's the Blueprint."
Get the whole plugin
Stats
119
Stars
34
Forks
Quiet
Maintenance
Shell
Language
7mo ago
Last commit
7mo ago
Created
11h ago
Added