# Poteto Mode

Poteto's agent style for concise, detailed responses, deliberate subagents, unslopped...

- Repository: https://github.com/michael-denyer/pstack-claude (3725 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-30
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add michael-denyer/pstack-claude --skill poteto-mode -g -a claude-code -y`
Codex: `npx skills add michael-denyer/pstack-claude --skill poteto-mode -g -a codex -y`
Cursor: `npx skills add michael-denyer/pstack-claude --skill poteto-mode -g -a cursor -y`
Gemini CLI: `npx skills add michael-denyer/pstack-claude --skill poteto-mode -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add michael-denyer/pstack-claude`

## Description

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Poteto mode

Bundled skills live at `../<name>/SKILL.md` from this file, so put this file's absolute path in every `poteto-agent` prompt.

## Platform Adaptation

These skills use Claude Code tool names (the `Skill` tool, the `Agent` tool, `AskUserQuestion`) and the Claude model names the `Agent` tool accepts, as each Models section lists them. On Claude Code they work as written. On Codex, read [`references/codex-tools.md`](references/codex-tools.md) for the Codex equivalent of a Claude tool, model, or skill named by these workflows. On Pi, read [`references/pi-tools.md`](references/pi-tools.md) instead. On GitHub Copilot, CLI or app, read [`references/copilot-tools.md`](references/copilot-tools.md) instead. On Muse, read [`references/muse-tools.md`](references/muse-tools.md) instead. Other runtimes can discover the same Agent Skills tree, but they must use their own tool, model, and configuration equivalents. No one of these mappings is a cross-runtime map.

Use the session's task-tracking tools for the todolist. On Claude Code these are `TaskCreate` and `TaskUpdate`, or `TodoWrite` when configured. Availability depends on the model; `CLAUDE_CODE_ENABLE_TODO_TOOLS=1` enables them through the environment or a project's `.claude/settings.local.json` `env` block. See the [task-tool documentation](https://code.claude.com/docs/en/tools-reference#task-tool-availability). If no task-tracking tool is available, keep an uncommitted `todo.md` Markdown checklist in the work dir, next to the decision trail, with the playbook steps verbatim and each `skip: <reason>` line. When several sessions share the checkout, name it `.audit/<task-slug>.todo.md`, beside that session's `.audit/<task-slug>.tsv` trail, so they never write one file.

## Non-negotiables

The Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.

The rest: https://github.com/michael-denyer/pstack-claude/blob/HEAD/plugins/pstack/skills/poteto-mode/SKILL.md