cc-agent

cc-agent is a command for Claude Code from TheLobbi/claude. It costs 0 tokens per session (439 once invoked), scanned A, original, MIT.

A command for creating and managing custom agents in Claude Code. An agent is a configured helper with a specific role, such as testing, debugging, research, or security review.

In plain words
What is it for?
Use it to create named agents, list available agents, inspect their details, or use built-in roles for code exploration, planning, testing, reviews, and documentation.
Why use it?
It gives repeated coding tasks a defined role and set of instructions instead of configuring a helper from scratch each time.

Command for Claude Code

Part of the claude-orchestration plugin — 49 commands, 9 agents shipped together

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 commands/thelobbi/claude/cc-agent
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 49 commands, 9 agents.

Wrote 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.

agentmods badge for cc-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/thelobbi/claude/cc-agent.svg)](https://agentmods.dev/commands/thelobbi/claude/cc-agent)
Your own site
<a href="https://agentmods.dev/commands/thelobbi/claude/cc-agent"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/cc-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 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 $0.00000 $0.00439
Opus 5 $0.00000 $0.00219
Sonnet 5 $0.00000 $0.00088
Haiku 4.5 $0.00000 $0.00044

Measured 3d ago against content hash fd4d16628fb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-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 3d 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.

.claude/commands/cc-agent.md · 96 lines

What it actually says

/cc-agent — Custom Agent Builder

Create and manage custom agents for Claude Code.

Usage

/cc-agent [action] [name]

Actions

create

Create a new custom agent.

/cc-agent create                      # Interactive
/cc-agent create my-specialist        # Create named agent

list

List all available agents.

/cc-agent list                        # Show all agents
/cc-agent list --built-in             # Show built-in sub-agent types

info

Show details about an agent.

/cc-agent info agent-name

Built-in Sub-Agent Types

Type Purpose
general-purpose Multi-step tasks
Explore Fast codebase exploration
Plan Architecture planning
claude-code-guide Claude Code questions
researcher Deep research
test-writer Test generation
code-reviewer Code quality review
debugger Error diagnosis
doc-writer Documentation
security-reviewer Security audit

Custom Agent Template

---
name: my-agent
description: What this agent does
tools:
  - Read
  - Write
  - Edit
  - Bash
  - Glob
  - Grep
model: claude-sonnet-5
---

# Agent Name

Expert description and instructions.

## Capabilities
- What this agent can do

## Workflow
1. Step one
2. Step two

## Guidelines
- Rule one
- Rule two

Implementation

When invoked:

For create:

  1. Ask about the agent's domain expertise
  2. Ask about required tools
  3. Ask about model preference
  4. Generate agent markdown file
  5. Save to .claude/agents/ directory
  6. Verify the agent loads correctly

For list:

  1. Scan .claude/agents/ for agent files
  2. Scan plugins/*/agents/ for plugin agents
  3. List all with name, description, tools
  4. Show built-in types separately
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. 3d ago First seen · 96 lines · 0 tokens per session scan A fd4d16628fb1

Subscribe to this mod's changes

cc-agent is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 439 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 2026-08-31.