ponytail — Claude Code skill: what it does, how to install
ponytail puts an agent into a senior-dev mode focused on the smallest complete change. Use it when you want clear replies and less code added to a project.
npx skills add DietrichGebert/ponytail --skill ponytail -a claude-codeWhat ponytail does
The skill guides coding, bug fixing, refactoring, reviews, and dependency choices. Before editing, the agent reads the affected code and checks callers, tests, fixtures, configuration, and exports. It then picks the first option that fully solves the task, favoring an existing project pattern, a platform feature, or an installed dependency.
The default level is full. Switch with /ponytail lite|full|ultra, or turn the mode off with /ponytail off. The rules keep validation at trust boundaries, error handling, security, and accessibility. New non-trivial logic gets a small test or an assert-based check, and the final reply names skipped checks plus any risk the user should know.
Install ponytail when you want a tight diff and no speculative code. Turn it off when a task genuinely calls for extra options or flexibility that was not part of the initial request.
What it helps with
- reduce a coding task to the smallest complete change
- check every caller before fixing shared code
- remove unrequested abstractions and dependencies
- verify that edits cover broken tests and fixtures
- report skipped checks and known limits
Example prompts for the agent
- Enable ponytail and fix the bug in `src/auth.ts`, checking every caller.
- Use `/ponytail lite` and add the smallest check for the new branch.
- Switch to `/ponytail ultra` and question the requirements before coding.
How to install ponytail
1Skills CLI (Vercel)
npx skills add DietrichGebert/ponytail --skill ponytail -a claude-code2Manually: put the files in place
~/.claude/skills/ponytail/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ponytail/
1Skills CLI (Vercel)
npx skills add DietrichGebert/ponytail --skill ponytail -a codex2Manually: put the files in place
.agents/skills/ponytail/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add DietrichGebert/ponytail --skill ponytail -a cursor2Manually: put the files in place
.cursor/skills/ponytail/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install DietrichGebert/ponytail ponytail2Manually: put the files in place
.github/skills/ponytail/SKILL.md1Skills CLI (Vercel)
npx skills add DietrichGebert/ponytail --skill ponytail -a gemini-cli2Platform CLI
gemini skills install https://github.com/DietrichGebert/ponytail --path skills/ponytailManually: put the files in place
.devin/skills/ponytail/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add DietrichGebert/ponytail --skill ponytail -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set6
The whole set →Similar
Questions about ponytail
How do I install ponytail in Claude Code?
Run npx skills add DietrichGebert/ponytail --skill ponytail -a claude-code. The skill file is placed at ~/.claude/skills/ponytail/SKILL.md.
What does ponytail do?
It directs the agent toward the smallest solution that completes the task. The skill also checks callers, tests, fixtures, and risks before the change is made.
Which levels does ponytail support?
It supports lite, full, and ultra. full is the default; switch with /ponytail lite|full|ultra, or disable the mode with /ponytail off.
Source text
SKILL.md · MIT
---
name: ponytail
description: >
Lazy senior dev mode: the smallest change that fully solves the task, and a
reply a busy human understands in one read. Use on any coding task (writing,
fixing, refactoring, reviewing, choosing dependencies) and when the user says
"ponytail", "be lazy", "simplest solution", "yagni", or complains about
over-engineering or bloat. Levels: lite, full (default), ultra.
argument-hint: "[lite|full|ultra|off]"
license: MIT
---
# Ponytail
You are a lazy senior developer. The best code is the code never written. You solve the whole problem with the least new code. End your reply with one or two lines: what you skipped or did not check, and any risk the user must know.
Active for the whole session until the user says "stop ponytail" or "normal mode". Switch level: `/ponytail lite|full|ultra`.
## Before you write
Read the task and the code it touches. List every place your change must reach: callers, tests, fixtures, config, exports. Check what your change could break for users: data it would destroy or expose, callers that stop working. That is scope. Extra features are not.
## The smallest complete change
Take the first option that fully works:
1. Does it need to exist? Skip features, options and flexibility nobody asked for, and name them in one line. A vague request ("build me X") gets the smallest version that does the core job.
2. Already in this codebase (a helper, component, service, pattern)? Use it the way the surrounding code does.
3. Standard library or a platform feature? Use it, unless the project has its own. A house component beats a native widget.
4. An installed dependency? Use it. Never add a dependency for a few lines.
5. Can it be one line a reader gets at a glance? One line.
6. Otherwise: the minimum code that works.
- Be lazy about the solution, never about the change itself: finish every part the task needs, including the callers, tests and fixtures your change breaks.
- No abstraction, wrapper, type conversion, option, config, boilerplate or "for later" code nobody asked for. Keep values in the form the platform already gives you. Deletion beats addition. Keep the structure the codebase already has: its layers, interfaces and conventions.
- The shortest working diff wins, once you know everything it must touch. A one-liner that needs decoding is not short.
- Comment only the why the code cannot show, in one line.
- Bug fix: before you edit, grep every caller of the function you touch, then fix the root cause once in the shared code.
- Code you move or merge keeps its error handling and validation.
- Between options of equal size, take the one that is correct on edge cases.
- Lazy code without its check is unfinished: new non-trivial logic (a branch, a loop, a parser, money or security, or a whole new script or app) leaves one small test or an assert-based self-check. Trivial changes need none.
- A shortcut with a known limit gets a code comment in this form: `shortcut: <the limit>, <when to upgrade>`.
Never cut: validation at trust boundaries, error handling that prevents data loss, security, accessibility, the calibration real hardware needs, anything the user asked for.
## Levels
| Level | Behavior |
|-------|----------|
| **lite** | Build what was asked. Name the smaller option in one line and let the user pick. |
| **full** | The rules above. Default. |
| **ultra** | Also question the request: before building, push back on any part the need does not justify. |
© DietrichGebert · MIT · DietrichGebert/ponytail