Amp Cli

Community

paulinevos

amp-cli

Use ampcode.com's CLI when the user asks to start an orb or thread on Amp, hand work to Amp with summarized context, continue a thread, or inspect and manage Amp work.

Overview

Publisher	paulinevos
Repository	`claude-stuff`
Skill name	`amp-cli`
Stars	64
Forks	0
Bundled files	1
License	MIT
Links	Skill source Repository

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 paulinevos on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/paulinevos/claude-stuff/tree/main/plugins/amp-workflow/skills/amp-cli
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/paulinevos/claude-stuff/tree/main/plugins/amp-workflow/skills/amp-cli

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/paulinevos/claude-stuff.git /tmp/claude-stuff
mkdir -p .claude/skills
cp -r /tmp/claude-stuff/plugins/amp-workflow/skills/amp-cli .claude/skills/amp-cli

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Amp Cli 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 Amp Cli 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 Amp Cli 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.

Amp CLI

When asked to start an orb, start a thread on Amp, or hand work to Amp, actually launch it through the CLI and return its URL. Writing this skill does not itself authorize launching an Amp task.

Check availability

Run command -v amp, amp version, and amp --help. If PATH misses it, check ~/.local/bin/amp and ~/.amp/bin/amp. Read relevant subcommand help for unfamiliar operations: Amp changes quickly.

If missing, report it. When installation is requested, download and inspect https://ampcode.com/install.sh, run the official installer with required permissions, and verify help/version. Existing shells may need the absolute executable path after the installer updates PATH.

Check amp account list. An existing AMP_API_KEY can authenticate too; check presence without revealing its value. If needed, use amp login when authorized and leave browser sign-in to the user. Successful help output does not establish authentication.

Prepare context

Write a self-contained summary to a temporary UTF-8 file using a file-writing tool. Include the outcome and acceptance criteria, repository/project and branch or commit, relevant files and links, decisions and constraints, findings, completed work, next steps, reproduction/tests and known failures, and the scope of authorized actions. Distinguish facts from hypotheses. Omit unrelated history and credentials. Feed this file through stdin rather than interpolating conversation text into a shell command.

Run in the relevant checkout. For repository work, check amp projects status --json or select a known project explicitly; resolve a missing project before launching. No-project orbs are appropriate for tasks needing no repository. Orbs cannot assume access to local paths, uncommitted changes, or unpublished commits. Supply necessary diffs/files through prompt context or --attach and explain their use. Do not push merely to facilitate a handoff without authorization.

Launch and follow up

For an orb or a generic remote handoff to a thread on Amp, use:

sh
amp -ox --title 'Investigate the failing build' --project owner/repo < /tmp/amp-handoff.txt

Replace examples with actual values. -ox submits the prompt and returns a thread URL while work continues remotely. Report launched work, not completed work. Preserve requested mode, visibility, and orb size; otherwise use defaults. Do not silently change a requested executor.

For explicitly local work:

sh
amp -x --executor local --no-archive-after-execute --stream-json < /tmp/amp-handoff.txt

This waits for the turn. Extract the thread ID from structured output according to the installed version's schema. For a specified runner, use --executor runner:<id> and optionally --runner-dir <absolute-path>.

Follow up on a known remote thread without creating another:

sh
amp threads continue T-actual-id -ox < /tmp/amp-followup.txt

Use -x for existing local work. amp threads new creates an empty thread: use only when an empty thread is requested. Interactive amp --executor orb waits for the first prompt and is unsuitable for an unattended launch. If submission is uncertain, inspect recent threads before retrying. Add --no-archive-after-execute when streaming an orb turn that should stay active.

Manage Amp

Check each command's --help for exact arguments.

Need	Commands
Find work	`amp threads list`, `amp threads search`, `amp top`
Read results	`amp threads markdown <id>`, `amp threads export <id>`
Costs/context	`amp usage`, `amp threads usage <id>`, `amp threads context <id>`
Projects	`amp projects status --json`, `amp projects list`, `amp projects get`
Organization	`amp threads rename`, `amp threads label`, `amp threads archive`
Integrations	`amp tools list`, `amp plugins list`, `amp skill list`, `amp mcp doctor`

Sharing, deletion, account switching, and changing projects/integrations need corresponding user intent. Orb service commands manage processes inside an orb; do not assume they target a remote orb from a local checkout. Verify synchronization support in installed help before applying remote changes locally.

For cap alerts, use the sibling amp-usage-watch skill. Consult the official CLI, orb, and thread docs when help is insufficient.

Bundled files

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

agents/openai.yaml1 KB

Frequently asked questions

What does the Amp Cli AI skill do?

Use ampcode.com's CLI when the user asks to start an orb or thread on Amp, hand work to Amp with summarized context, continue a thread, or inspect and manage Amp work.

Why use Amp Cli on TypingMind?

Because you install it once and use it with any model. Amp Cli 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 Amp Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/paulinevos/claude-stuff/tree/main/plugins/amp-workflow/skills/amp-cli. 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 Amp Cli?

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 Amp Cli?

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

Is the Amp Cli AI skill free?

Yes. It is published on GitHub by paulinevos 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

Auteur

NousResearch

OrganizationPopular

Design and build cinematic, award-level web pages.

Excalidraw

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

Simple English

Rewrite text to ASD-STE100 Simplified Technical English.

Watchers

Poll RSS, JSON APIs, and GitHub with watermark dedup.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Amp CLI

Check availability

Prepare context

Launch and follow up

Manage Amp

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now