toolpiper-setup

toolpiper-setup is a skill for Claude Code from ModelPiper/toolpiper. It costs 70 tokens per session (629 once invoked), scanned A, original, MIT.

A setup guide for connecting Claude Code to ToolPiper, a local macOS app that provides agent tools.

In plain words
What is it for?
For fixing missing-app, stopped-app, startup, authentication-state, and wrong-machine connection problems.
Why use it?
It helps diagnose whether ToolPiper is installed, running, and reachable when a connection fails, without changing Claude configuration.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the toolpiper plugin — 1 skill shipped together

Good fit For fixing missing-app, stopped-app, startup, authentication-state, and wrong-machine connection problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modelpiper/toolpiper/toolpiper-setup
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.

Any agent
npx skills add ModelPiper/toolpiper --skill toolpiper-setup
Clone the repo
git clone --depth 1 https://github.com/ModelPiper/toolpiper

Made for: Claude Code.

Or install toolpiper, the plugin that ships this one along with the rest of its 1 skill.

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 toolpiper-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/modelpiper/toolpiper/toolpiper-setup/github.svg)](https://agentmods.dev/skills/modelpiper/toolpiper/toolpiper-setup)
Your own site
<a href="https://agentmods.dev/skills/modelpiper/toolpiper/toolpiper-setup"><img src="https://agentmods.dev/badge/skills/modelpiper/toolpiper/toolpiper-setup/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.

agentmods 80×15 button for toolpiper-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/modelpiper/toolpiper/toolpiper-setup"><img src="https://agentmods.dev/badge/skills/modelpiper/toolpiper/toolpiper-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.00629
Opus 5.5 $0.00028 $0.00252
Sonnet 5.5 $0.00014 $0.00126
Haiku 4.5 $0.00007 $0.00063

Measured 6d ago against content hash e4679a43a5f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

toolpiper-setup scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. Listening? `curl -s http://127.0.0.1:9998/health` returns JSON containing `"status":"ok"`.
plugins/toolpiper/skills/toolpiper-setup/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ToolPiper setup

The toolpiper MCP server this plugin declares is ToolPiper.app itself, listening on http://127.0.0.1:9998/mcp. The plugin runs nothing: it points your agent (Claude Code or Codex) at the app. If the server is unreachable, the app is not installed, not running, or still starting.

Diagnose, in this order

  1. Installed? ls /Applications/ToolPiper.app succeeds when it is.
  2. Running? pgrep -x ToolPiper prints a process id when it is.
  3. Listening? curl -s http://127.0.0.1:9998/health returns JSON containing "status":"ok".

Fix

  • Not installed. Tell the user to download the DMG from https://modelpiper.com/download, drag ToolPiper.app to /Applications, and launch it once, or to install it with Homebrew: brew tap modelpiper/tap, brew trust modelpiper/tap, brew install --cask toolpiper. It requires macOS 26 or later on Apple Silicon. The free tier needs no account.
  • Installed but not running. Run open -a ToolPiper and wait until /health answers (a few seconds). Then reconnect: in Claude Code run /mcp or start a new session; in Codex start a new session.
  • Running but the client reports "needs authentication". Loopback connections need no sign-in from Claude Code: this is stale session state, so start a new session. Codex signs in to ToolPiper once: run codex mcp login toolpiper and approve ToolPiper's consent page.
  • The agent is on a different machine from ToolPiper. The plugin's server URL is loopback only. Point the user at ToolPiper's remote-access documentation, https://modelpiper.com/docs/toolpiper, rather than editing configuration for them.

Rules

  • Never edit the agent's own settings or any MCP server list. The plugin already declares the server; a second entry does not help.
  • Install ToolPiper only from the DMG at modelpiper.com or the official Homebrew tap above, and only when the user asks. Never from another script or package source.
  • Read nothing from the user's files to reach ToolPiper. The loopback server needs no credentials, so the three checks above are the whole diagnosis.

Read the full file on GitHub · 43 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 Changed · +6 lines · +2 tokens per session e4679a43a5f0
  2. 1mo ago First seen · 37 lines · 68 tokens per session scan A c323d23fb8b1

Subscribe to this mod's changes

toolpiper-setup is a skill published in the GitHub repository ModelPiper/toolpiper (2 stars, last pushed 6d ago), licensed MIT. It adds 70 tokens to every session and 629 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

Related

Other skills, from other repositories

localvoxtral-doctor

Use when the user's localvoxtral dictation misbehaves, for example a dictation did not join this session, its text was not inserted, or speech or polish failed. Names the localvoxtral commands that check the setup and read the app's log.

T0mSIlver/localvoxtral · 59 tokens

ace-music

Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.

fspecii/openfelix · 64 tokens

bird

Post, read, search, and reply on X (Twitter) using your browser cookies — no API key required.

fspecii/openfelix · 25 tokens

finance-lookup

Look up real-time stock prices, currency exchange rates, and commodity prices. Use when the user asks about stock prices (e.g. "AAPL price"), currency conversion (e.g. "1 dollar in lei", "EUR to RON"), commodity prices (e.g. "price of 1 gram of gold in euros", "silver price", "oil price"), or crypto prices (e.g.…

fspecii/openfelix · 95 tokens

youtube-info

Extract description and captions/transcript from a YouTube video without opening the browser. Use when the user asks what a video is about, wants a summary, or asks about video content. Accepts a YouTube URL (use the URL returned by youtube-search if available) or a plain search query. Never call youtube-search before…

fspecii/openfelix · 76 tokens

youtube-search

Search YouTube and open the first matching video in the browser. Returns the video title and URL. Use when the user asks to play, watch, find, show, or search for something on YouTube. Do NOT use when the user only wants to know what a video is about — use youtube-info directly for that instead.

fspecii/openfelix · 69 tokens