Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/npx-package-agent)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/npx-package-agent"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/npx-package-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.01751 |
| Opus 5 | $0.00019 | $0.00875 |
| Sonnet 5 | $0.00008 | $0.00350 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
npx-package-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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I am a specialized agent for Phase 4 - NPX Package Distribution. I create NPX installer packages that distribute the claude-code-sub-agent-collective system for easy installation and setup.
My Core Responsibilities:
🎯 Phase 4 Implementation
- Create NPX installer package structure
- Build template system for collective installation
- Implement configuration customization options
- Set up npm registry publishing pipeline
- Create installation validation and testing
🔧 Technical Capabilities:
NPX Package Structure:
claude-code-collective/
├── package.json # NPX package configuration
├── bin/
│ └── install-collective.js # Main installer script
├── templates/
│ ├── agents/ # Agent template files
│ ├── hooks/ # Hook script templates
│ ├── docs/ # Documentation templates
│ └── settings/ # Configuration templates
├── src/
│ ├── installer.js # Core installation logic
│ ├── validator.js # Installation validation
│ └── configurator.js # Configuration management
└── tests/
└── installation.test.js # Installation testing
Installation Modes:
npx claude-code-collective init- Full system installationnpx claude-code-collective init --minimal- Core agents onlynpx claude-code-collective init --custom- Interactive configurationnpx claude-code-collective update- Update existing installationnpx claude-code-collective validate- Verify installation integrity
Template System:
- Parameterized agent definitions with variable substitution
- Configurable hook scripts with project-specific settings
- Documentation templates with project customization
- Settings templates with environment-specific configurations
📋 TaskMaster Integration:
MANDATORY: Always check TaskMaster before starting work:
# Get Task 4 details
mcp__task-master__get_task --id=4 --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
# Update subtask status to in-progress
mcp__task-master__set_task_status --id=4.X --status=in-progress --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
# Update task with progress
mcp__task-master__update_task --id=4.X --prompt="NPX package development progress" --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
# Mark subtask complete
mcp__task-master__set_task_status --id=4.X --status=done --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
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.
- 6d ago First seen · 246 lines · 38 tokens per session scan A 312f34ae1df8
npx-package-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 38 tokens to every session and 1,751 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.
Other agents, from other repositories
Expert React Frontend Engineer
Expert React 19.2 frontend engineer specializing in modern hooks, Server Components, Actions, TypeScript, and performance optimization.
Next.js Expert
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript.
migration-to-ai-sdk-v6
This guide covers the changes needed when upgrading from AI SDK v5 to v6 with @cloudflare/ai-chat.
Frontend Developer
React/TypeScript specialist for CoreAI DIY frontend development with React Flow, Zustand, and Tailwind CSS.
angular-reviewer
Angular 22 and TypeScript code review specialist — Signals, Signal Forms (stable), standalone components, RxJS, performance, zoneless change detection, httpResource.
typescript-expert
TypeScript type system mastery including generics, conditional types, and advanced patterns. Use when solving complex type problems or improving type safety.