Borrowing it
Nothing to install: this file belongs to RegardV/LegendaryTeam_For_Claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RegardV/LegendaryTeam_For_Claude/main/.claude/commands/spawn-subagent.mdgit clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_ClaudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/regardv/legendaryteam_for_claude/spawn-subagent)<a href="https://agentmods.dev/commands/regardv/legendaryteam_for_claude/spawn-subagent"><img src="https://agentmods.dev/badge/commands/regardv/legendaryteam_for_claude/spawn-subagent.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01780 |
| Opus 5 | $0.00000 | $0.00890 |
| Sonnet 5 | $0.00000 | $0.00356 |
| Haiku 4.5 | $0.00000 | $0.00178 |
Grade A, and why
spawn-subagent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spawn-subagent - Dynamic Agent Spawning
Purpose
Spawns a specialized subagent dynamically for a specific task, enabling flexible team composition based on runtime requirements.
Usage
/spawn-subagent [role] [task]
/spawn-subagent coder "Implement user profile API"
/spawn-subagent security "Review authentication flow"
/spawn-subagent database "Optimize slow queries"
Available Roles
| Role | Agent | Specialization |
|---|---|---|
coder |
@CodeAgent | General implementation |
database |
@DatabaseAgent | Schema, migrations, queries |
api |
@APIAgent | REST/GraphQL endpoints |
ui |
@UIAgent | Frontend components |
security |
@SecurityAgent | Security review, auth |
test |
@TestAgent | Unit/integration tests |
e2e |
@E2ERunner | End-to-end tests |
perf |
@PerformanceOptimizer | Performance optimization |
doc |
@DocAgent | Documentation |
refactor |
@RefactorAgent | Code refactoring |
architect |
@ArchitectureAgent | Architecture decisions |
planner |
@Planner | Task decomposition |
verifier |
@Verifier | Quality assurance |
reflect |
@ReflectionAgent | Self-critique |
Options
| Option | Description |
|---|---|
| --confidence N | Override confidence (0-100) |
| --iterate | Enable iteration mode |
| --max-iterations N | Max iterations (default: 3) |
| --priority high/med/low | Task priority |
| --depends-on ID | Declare dependency |
| --blocking | Wait for completion |
| --background | Run in background |
Workflow
1. Agent Spawning
/spawn-subagent security "Review new payment endpoint"
Spawning @SecurityAgent...
Configuration:
├─ Task: Review new payment endpoint
├─ Confidence: Auto-detected (analyzing...)
├─ Priority: High (security-related)
├─ Mode: Standard (no iteration)
└─ Timeout: 30 minutes
Agent spawned successfully.
Team ID: team-sec-001
2. Confidence Analysis
Before execution, confidence is assessed:
@ConfidenceAgent analyzing task...
Analysis:
├─ Task type: Security review
├─ Codebase familiarity: High (similar patterns exist)
├─ Complexity: Medium
├─ Risk level: High (payment-related)
└─ Precedent: 3 similar reviews completed
Confidence Score: 65%
Routing: QUEUE FOR REVIEW (security-critical)
Human approval required. Added to review queue.
Run /approve-task team-sec-001 to proceed.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 276 lines · 0 tokens per session scan A 9fea744ec636
spawn-subagent is a command published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,780 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
plan-workflow
Generate a skill chain plan for a high-level goal by analyzing the skills registry for input/output compatibility.
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.
mpm-init
Initialize or update project for Claude Code and MPM.
orquestar
Macro (4 fases) vs micro (8 pasos): el core del DT resume el flujo en 4 fases (Clarificar → Planificar y validar → Ejecutar → Entregar). Este comando es el desglose en 8 pasos; no es un pipeline alternativo. Fuente canónica del par macro/micro: regla 00-orquestador-core (no redefinir el modelo en otros lugares…
init-rules
Auto-generate .claude/rules/ — path-scoped coding conventions from project analysis. Re-run after codebase changes to update rules while preserving manually added conventions.