create-agent

A command that creates and validates a specialized coding agent through an interactive or automated setup process.

In plain words
What is it for?
Creating agents for areas such as DevOps, security, or programming languages, with options for interactive setup, templates, and validation.
Why use it?
It gives new agents a defined category, optional template, and validation stages, reducing the work of designing their structure from scratch.

Command for Claude Code

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

Made for: Claude Code.

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 786 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 $0.00786
Opus 5 $0.00000 $0.00393
Sonnet 5 $0.00000 $0.00157
Haiku 4.5 $0.00000 $0.00079

Measured 2d ago against content hash a760ee93bd09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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.

.claude/commands/create-agent.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/create-agent

Quick Usage: /create-agent [agent-name] --category=devops --interactive=true

Interactive wizard for creating, validating, and integrating new specialized agents into the AI ecosystem.

Core Parameters

Parameter Type Purpose Example
agent-name string Agent identifier k8s-security-scanner
--category select Agent category core, devops, security, data-ai
--interactive boolean Interactive mode true, false
--template string Base template language-specialist, cloud-expert
--skip-validation boolean Skip validation phases false (not recommended)

Quick Examples

```bash

Interactive creation

/create-agent k8s-security-scanner --category=security --interactive=true

Template-based

/create-agent rust-web-specialist --template=language-specialist

Non-interactive (expert mode)

/create-agent custom-agent --category=devops --interactive=false ```

What It Does

8-Phase Agent Lifecycle:

Phase Focus Duration Key Activities
1. Discovery Needs & gap analysis 10-15 min Analyze requirements, check duplicates
2. Design Architecture & persona 15-25 min Design capabilities, create persona
3. Prompting Prompt engineering 10-15 min Craft system prompts, examples
4. Generation File creation 5-10 min Generate .md, .json, docs
5. Review Quality validation 10-15 min Code review, best practices check
6. Documentation Ecosystem integration 10-15 min Update registry, CLAUDE.md, guides
7. Testing Validation scenarios 15-20 min Create tests, validate invocations
8. Finalization Approval & deployment 5-10 min Final review, activation

Total Time: 90-120 minutes

Quality Assurance

  • ✅ Duplicate prevention (searches 65-agent ecosystem)
  • ✅ Capability gap validation
  • ✅ Prompt quality review
  • ✅ Documentation completeness check
  • ✅ Test scenario coverage
  • ✅ Registry integration validation

Read the full file on GitHub · 95 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 · 95 lines · 0 tokens per session scan A a760ee93bd09

Subscribe to this mod's changes

create-agent is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 786 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.