Pi Update logo

Pi Update

Organization
vanillagreencom
pi-update

Load to check the kendex Pi extensions against a Pi release, fix what breaks, and record the verdict.

Overview

Publishervanillagreencom
Repositorykendex
Skill namepi-update
Stars
91
Forks
37
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vanillagreencom on GitHub. Read the source before you install it.

Installation

Install the Pi Update AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vanillagreencom/kendex/tree/main/.agents/skills/pi-update
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vanillagreencom/kendex.git /tmp/kendex
mkdir -p .claude/skills
cp -r /tmp/kendex/.agents/skills/pi-update .claude/skills/pi-update
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pi Update in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pi Update on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pi Update is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Project Instructions

Problems with a kendex-owned skill go through kendex report; check ownership in the file first.

Pi update

Checks pi-extensions/* against a Pi release and records one verdict. The record is pi-extensions/pi-update.audit.md, the one compatibility record. The marker pi-extensions/pi-update.state.json only says which releases were read. The rule the verdict applies is pi-extensions/AGENTS.md.

To audit a Pi release, follow workflows/audit-release.md. A step this file cites is that workflow's step.

Release handling

  • Pin nothing, freeze nothing, hold no release back. Fleet lanes follow the vendor's latest Pi through the fleet's fleet-cli-update. A hold verdict stops a peer floor from rising, never a lane from updating.
  • Start the run as soon as a new release is seen.
  • The Linear item a new Pi release creates, and every follow-up a failing run files, is priority High (2), never Backlog. A failing run is fixed forward, never by pinning Pi to an older release.

Input

  • No argument: the target is npm's current latest of @earendil-works/pi-coding-agent.
  • A version: that version is the target. Every source is still fetched.
  • A pasted changelog: the authoritative entry list for the range; changelog fetching is skipped. The target is the highest released version header in the paste, and workflows/audit-release.md step 1 captures that version.

Audit record

Name each Linear item by id only, beside the Pi entry and package it concerns. Do not state its status, priority or adoption.

The record holds: the Marker `<old>` → `<new>`. line, where <old> is lastVersion at run start and <new> the target; the sources fetched; every classified entry; and a ## Verdict section. The Verdict section opens with the verdict and then this summary, in this form:

markdown
Verdict: `roll`.

- Target release: `<version>`, npm `@earendil-works/pi-coding-agent@<version>` integrity `<sha512-…>`, upstream source commit `<40-hex>`.
- Entries examined: <the releases and sources read, and the Breaking Changes entries the table lists>.
- Tested extension commit: `<40-hex>`.
- Evidence: <the `<run>` directory, the fixtures, tests and CI runs step 4 and step 6 ran, and the Pi version each resolved>.

The Breaking Changes table follows. A roll clears <new>; a hold clears <old>. What pi-extensions/package-policy.test.mjs refuses in the record is the Pi update audit bullet of pi-extensions/AGENTS.md.

Final report

  • Releases covered, old marker to target, with dates, and the source keys that carried entries.
  • Entry counts per bucket, and the verdict with each blocking entry and the pi-hooks change it waits for.
  • Commits shipped, packages touched, and tests run with pass counts.
  • Deferred Optional entries with their reasons; the Non-impact log.
  • The tested extension commit, the marker commit, the npm-deploy item, and the refresh result.
  • How step 7's result was sent: from a lane, the exit status of lane-mail notice, which prints nothing on success; from the control VM, the receipt lane-mail peer send prints.
  • git status --short is clean.

Notes

  • Pi releases every package in lockstep under one version, so lastVersion covers the whole release.
  • pi update reconciles only git: and npm: entries in Pi's settings.json. kendex installs extensions as path packages, so a changelog entry about pi update does not reach them; say so in the record.
  • pi-tool-renderer replaces Pi's read, bash, edit, write, search and list renderers. A Pi change to their default look is a choice for the user, not an automatic mirror.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Pi Update AI skill do?

Load to check the kendex Pi extensions against a Pi release, fix what breaks, and record the verdict.

Why use Pi Update on TypingMind?

Because you install it once and use it with any model. Pi Update is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pi Update in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vanillagreencom/kendex/tree/main/.agents/skills/pi-update. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pi Update?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pi Update?

As many as you like. As long as a model supports skills, you can use Pi Update with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pi Update AI skill free?

Yes. It is published on GitHub by vanillagreencom under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇