pick-agent

pick-agent is a command for Claude Code from khanh-vu/claude-force. It costs 8 tokens per session (2,712 once invoked), scanned A, original, MIT.

A command for copying reusable agent definitions and their contracts from one project into another. An agent is a configured helper with a defined role, responsibilities, inputs, outputs, and limits.

In plain words
What is it for?
Use it to list available agents, copy one or more agents, choose a source project, and update the target project’s claude.json configuration.
Why use it?
It avoids recreating the same agent setup by hand and keeps the copied definition, contract, and project configuration together.

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/khanh-vu/claude-force/pick-agent
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

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 pick-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/khanh-vu/claude-force/pick-agent.svg)](https://agentmods.dev/commands/khanh-vu/claude-force/pick-agent)
Your own site
<a href="https://agentmods.dev/commands/khanh-vu/claude-force/pick-agent"><img src="https://agentmods.dev/badge/commands/khanh-vu/claude-force/pick-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,712 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 $0.00008 $0.02712
Opus 5 $0.00004 $0.01356
Sonnet 5 $0.00002 $0.00542
Haiku 4.5 $0.00001 $0.00271

Measured 5d ago against content hash 1eb40c2b11fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pick-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 5d 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/pick-agent.md · 495 lines

How it starts

The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pick Agent Command

Copy agent packs (definitions + contracts) from a source project to your target project.

Purpose

The /pick-agent command helps you:

  • Browse available agents from claude-force or another project
  • Copy agent definition files to your project
  • Copy agent contract files to your project
  • Update your claude.json configuration automatically
  • Reuse proven agent packs across projects

Usage

List Available Agents

/pick-agent --list

Copy Single Agent

/pick-agent python-expert

Copy Multiple Agents

/pick-agent python-expert code-reviewer database-architect

Specify Source Project

/pick-agent python-expert --source /path/to/claude-force

Copy from Different Project

/pick-agent python-expert --source /path/to/other-project --target /path/to/my-project

What Gets Copied

For each agent, the command copies:

  1. Agent Definition: agents/{agent-name}.md

    • Role and responsibilities
    • Skills and specializations
    • Deliverables format
    • Examples and patterns
  2. Agent Contract: contracts/{agent-name}.contract

    • Scope of authority
    • Core responsibilities
    • Input/output requirements
    • Quality gates
    • Collaboration protocol
  3. Configuration Entry: Updates claude.json

    • Agent metadata
    • File references
    • Domain tags
    • Priority level

Implementation

You should execute this command by:

  1. Import the PickAgentCommand class:
from claude_force.commands.pick_agent import PickAgentCommand
from pathlib import Path
  1. Determine source and target paths:

    • Source: claude-force installation or another project
    • Target: Current project or user-specified path
    • Default source: claude-force package location
    • Default target: Current working directory
  2. List available agents:

command = PickAgentCommand(
    source_project=Path("/path/to/claude-force"),
    target_project=Path("/path/to/my-project")
)

# List all available agents
available = command.list_available_agents()
print(f"Available agents: {', '.join(available)}")

Read the full file on GitHub · 495 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. 5d ago First seen · 495 lines · 8 tokens per session scan A 1eb40c2b11fe

Subscribe to this mod's changes

pick-agent is a command published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It adds 8 tokens to every session and 2,712 once invoked, about $0.0000 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 2026-08-31.