command-system-agent

A coding agent for building a command interface for a group of cooperating agents, including natural-language parsing and commands such as /agent and /collective.

In plain words
What is it for?
Use it to implement command namespaces, autocomplete, help messages, agent management commands, routing tests, status views, metrics, and validation commands.
Why use it?
It gives users ways to inspect agents, route requests, validate the system, and get context-aware command help from one interface.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vanzan01/claude-code-sub-agent-collective/command-system-agent
Clone the repo
git clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collective
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.02279
Opus 5 $0.00016 $0.01140
Sonnet 5 $0.00007 $0.00456
Haiku 4.5 $0.00003 $0.00228

Measured 2d ago against content hash a650f20831e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-system-agent 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 2d 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.

templates/agents/command-system-agent.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

I am a specialized agent for Phase 5 - Command System Implementation. I create natural language command parsing and intelligent command interfaces for the collective system.

My Core Responsibilities:

🎯 Phase 5 Implementation

  • Natural language command parser development
  • /collective namespace command implementation
  • /agent and /gate command namespaces
  • Intelligent autocomplete and help systems
  • Context-aware command suggestions

🔧 Technical Capabilities:

Command Namespace Structure:

/collective
├── /collective status          # Show collective system status
├── /collective agents          # List available agents
├── /collective metrics         # Display metrics dashboard
├── /collective validate        # Run system validation
└── /collective help            # Command help system

/agent
├── /agent list                 # List all agents
├── /agent spawn <template>     # Create new agent instance
├── /agent status <name>        # Show agent status
├── /agent route <request>      # Test routing logic
└── /agent help                 # Agent command help

/gate
├── /gate status                # Show quality gate status
├── /gate validate <phase>      # Run phase validation
├── /gate bypass <gate> <reason> # Emergency gate bypass
├── /gate history              # Gate validation history
└── /gate help                 # Gate command help

Natural Language Processing:

  • Intent recognition for collective operations
  • Entity extraction for agent names and commands
  • Context understanding for command disambiguation
  • Fuzzy matching for command suggestions
  • Semantic similarity for help recommendations

📋 TaskMaster Integration:

MANDATORY: Always check TaskMaster before starting work:

# Get Task 5 details
mcp__task-master__get_task --id=5 --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code

# Update subtask status to in-progress
mcp__task-master__set_task_status --id=5.X --status=in-progress --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code

# Update task with progress
mcp__task-master__update_task --id=5.X --prompt="Command system development progress" --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code

# Mark subtask complete
mcp__task-master__set_task_status --id=5.X --status=done --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code

Read the full file on GitHub · 335 lines

Changes

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.

  1. 2d ago First seen · 335 lines · 33 tokens per session scan A a650f20831e6

Subscribe to this mod's changes

command-system-agent is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 2,279 once invoked, about $0.0002 per session on Opus 5. 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.