cami: Command for Claude Code

.claude/commands/cami-new-agent.md

cami-new-agent is a command for Claude Code from lando-labs/cami. It costs 10 tokens per session (754 once invoked), scanned A, original, MIT.

A command workflow for creating a new CAMI agent from user requirements using an agent-architect specialist. CAMI is an agent framework with defined file and design conventions.

In plain words
What is it for?
Designing and saving new CAMI agents with metadata, an appropriate role, a methodology, and a selected model.
Why use it?
It turns a set of requirements into a structured agent file and includes checks that the result follows the framework’s standards.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

This is lando-labs/cami's own configuration. It tells Claude Code how to work on cami itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cami configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lando-labs/cami. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lando-labs/cami/main/.claude/commands/cami-new-agent.md
Clone the repo
git clone --depth 1 https://github.com/lando-labs/cami

Made for: Claude Code.

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 cami-new-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/lando-labs/cami/cami-new-agent.svg)](https://agentmods.dev/commands/lando-labs/cami/cami-new-agent)
Your own site
<a href="https://agentmods.dev/commands/lando-labs/cami/cami-new-agent"><img src="https://agentmods.dev/badge/commands/lando-labs/cami/cami-new-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 754 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00010 $0.00754
Opus 5 $0.00005 $0.00377
Sonnet 5 $0.00002 $0.00151
Haiku 4.5 $0.00001 $0.00075

Measured 6d ago against content hash c3c1146b37fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cami-new-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 6d 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/cami-new-agent.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CAMI New Agent Creation

Create a new CAMI agent using the @agent-architect specialist.

User Requirements

$ARGUMENTS

Workflow

Phase 1: Design Agent with @agent-architect

Invoke the @agent-architect agent with these instructions:

"Design a new CAMI agent with the following specifications:

User Requirements: $ARGUMENTS

Technical Requirements:

  • Target Directory: ~/cami-workspace/sources/my-agents
  • Starting Version: 1.0.0
  • Must follow CAMI agent architecture standards
  • Must include complete YAML frontmatter (name, version, description, tags, use_cases, color, model)
  • Must include 'Use this agent PROACTIVELY when...' in description
  • Must follow three-phase specialist methodology
  • Must select appropriate archetype (Technical Specialist, Quality Guardian, System Designer, or Integration Specialist)
  • Include version numbers for technical specialists (e.g., React 19+, Node.js 18+)
  • Set appropriate model (opus for complex reasoning, sonnet for most agents)

Please create a production-ready agent file and save it to the sources/my-agents directory."

Wait for @agent-architect to complete the agent design and save the file.

Phase 2: Verification

After agent creation, verify:

  1. Use list_agents MCP tool to confirm the new agent appears in the VC agents list
  2. Read the agent file to show the user what was created

Phase 3: Deployment Instructions

DO NOT auto-deploy the agent. Instead, provide the user with deployment instructions using the MCP tools:

✅ Agent Created Successfully!

📝 Agent Details:
  • Name: [agent-name]
  • Version: [version]
  • Description: [description]
  • Location: ~/cami-workspace/sources/my-agents/[agent-name].md

🚀 To deploy this agent to a project, use the CAMI MCP tools:

1. Deploy the agent:
   deploy_agents(
     agent_names: ["[agent-name]"],
     target_path: "/path/to/your/project",
     overwrite: false
   )

2. Update CLAUDE.md:
   update_claude_md(
     target_path: "/path/to/your/project"
   )

The agent will be available via @[agent-name]

Read the full file on GitHub · 106 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. 6d ago First seen · 106 lines · 10 tokens per session scan A c3c1146b37fb

Subscribe to this mod's changes

cami-new-agent is a command published in the GitHub repository lando-labs/cami (14 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 754 once invoked, about $0.0001 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 2026-09-01.