pipi_setup

pipi_setup is a command for Claude Code from amyotoff/open-pipi. It costs 0 tokens per session (613 once invoked), scanned A, original, MIT.

A setup command for personalizing an Open PiPi assistant after installation.

In plain words
What is it for?
Use it to collect an assistant description, run the bootstrap process, review generated files and environment settings, and validate the result.
Why use it?
It guides the operator through creating the assistant’s grounding files while keeping deployment, persistent runtime startup, and secret handling separate.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions AGENTS.md.

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/amyotoff/open-pipi/pipi_setup
Clone the repo
git clone --depth 1 https://github.com/amyotoff/open-pipi

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 pipi_setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/amyotoff/open-pipi/pipi_setup.svg)](https://agentmods.dev/commands/amyotoff/open-pipi/pipi_setup)
Your own site
<a href="https://agentmods.dev/commands/amyotoff/open-pipi/pipi_setup"><img src="https://agentmods.dev/badge/commands/amyotoff/open-pipi/pipi_setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 613 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 5.1 $0.00000 $0.00613
Opus 5 $0.00000 $0.00307
Sonnet 5 $0.00000 $0.00123
Haiku 4.5 $0.00000 $0.00061

Measured 6d ago against content hash 19e7ddcabc31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pipi_setup 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/pipi_setup.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are helping an operator personalize Open PiPi after installation.

Follow AGENTS.md and CODING_AGENT_INSTALLATION.md. This command is an explicit opt-in to the Gemini-backed bootstrap and its new grounding files; it is not permission to deploy, start a persistent runtime, or handle secrets.

What this command does

/pipi_setup runs the operator bootstrap flow:

  1. Collects a one-paragraph description of the assistant
  2. Calls pnpm bootstrap to generate grounding files
  3. Shows the generated files and .env variables to set
  4. Hands .env changes to the operator
  5. Validates the generated content and TypeScript

Step 1 — Get the description

If $ARGUMENTS is not empty, use it as the description and skip asking.

Otherwise ask the user:

Describe your assistant in one paragraph. Cover: who it's for, the main job-to-be-done, language, key people and their roles, any standing rules or constraints.

Wait for the response before continuing.


Step 2 — Run bootstrap

Bootstrap can overwrite an existing src/groundings/<slug> when the generated slug collides. Never run it automatically. Check git status --short, stop if src/groundings/ has uncommitted or untracked work, warn the operator about the collision risk, and obtain separate confirmation before continuing.

Run the bootstrap with pnpm:

pnpm bootstrap

Send the description to the running process over stdin. Do not interpolate user text into a shell command or write it to a tracked file. Show the full bootstrap output to the user.


Step 3 — Show the generated files

Read and display the contents of the created grounding files:

  • src/groundings/<slug>/grounding.md
  • src/groundings/<slug>/people.md
  • src/groundings/<slug>/operating.md

Ask the user: "Does this look right? Anything to change?"

If they request changes, edit the files directly, then continue.


Step 4 — Hand off .env values

Never open, print, or edit .env. Show the operator the two non-secret values emitted by bootstrap:

Read the full file on GitHub · 88 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 · 88 lines · 0 tokens per session scan A 19e7ddcabc31

Subscribe to this mod's changes

pipi_setup is a command published in the GitHub repository amyotoff/open-pipi (20 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 613 tokens. 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.