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.
npx skills add justnau1020/claude-os --skill new-mcp-toolgit clone --depth 1 https://github.com/justnau1020/claude-osWrote 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/skills/justnau1020/claude-os/new-mcp-tool)<a href="https://agentmods.dev/skills/justnau1020/claude-os/new-mcp-tool"><img src="https://agentmods.dev/badge/skills/justnau1020/claude-os/new-mcp-tool/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/justnau1020/claude-os/new-mcp-tool"><img src="https://agentmods.dev/badge/skills/justnau1020/claude-os/new-mcp-tool.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.00426 |
| Opus 5 | $0.00018 | $0.00213 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
new-mcp-tool 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 12d 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.
What it actually says
Add a New MCP Tool
Add a tool to the project's FastMCP server.
Arguments
$ARGUMENTS-- Tool name in snake_case (e.g.,get_user_profile)
Steps
1. Read the existing MCP server
Read the MCP server file to understand current tool patterns and the FastMCP setup.
2. Add the tool
@mcp.tool()
async def $ARGUMENTS(
param1: str,
param2: int = 10,
) -> str:
"""Clear description of what this tool does and when an LLM should use it.
Include example parameter values to help LLMs understand expected input.
Example: param1="example_value", param2=30
"""
...
3. Tool description conventions
The tool description is critical -- it's how LLMs decide when to call it:
- First sentence: what the tool does
- Second sentence: when to use it
- Include parameter examples inline
- Mention any constraints (rate limits, data availability)
4. Implementation conventions
- Async only: All tool functions must be
async def - Return strings: MCP tools return string responses for LLM consumption
- Actionable errors: If something fails, return a helpful error string, not a generic one
- Respect data boundaries: All data queries should respect the project's access control and data validation rules
5. Write tests
Add tests for the new tool's logic. Test:
- Happy path with valid parameters
- Error handling with invalid parameters
- Data validation on returned data
6. Verify
pytest tests/ -v -k "mcp"
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.
- 12d ago First seen · 65 lines · 36 tokens per session scan A 7ecabf295c74
new-mcp-tool is a skill published in the GitHub repository justnau1020/claude-os (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 426 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 2026-08-31.
Other skills, from other repositories
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
env-manager
An environment-variable manager for project settings stored outside the code, often in .env files. It checks variable definitions and usage while keeping secret values out of reports and terminal output.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.