ponytail

NWBZPWNR — a Ponytail fork

He says nothing. He writes one line. It works.

80-94% less code · 3-6× faster · 47-77% cheaper
_{Median of 10 runs across Haiku, Sonnet, and Opus. Reproduce it yourself.}

---

NWBZPWNR — a fork of ponytail. Same lazy senior dev, plus extra skills (ponytail-skill, ponytail-claude-md).

You know him. Long ponytail. Oval glasses. Has been at the company longer than the version control. You show him fifty lines; he looks at them, says nothing, and replaces them with one.

Ponytail puts him inside your AI agent.

Before / after

You ask for a date picker. Your agent installs flatpickr, writes a wrapper component, adds a stylesheet, and starts a discussion about timezones.

With ponytail:

<!-- ponytail: browser has one -->
<input type="date">

More survivors in examples/.

Numbers

Five everyday tasks (email validator, debounce, CSV sum, countdown timer, rate limiter), three models, three arms: no skill, the caveman skill, and ponytail. Ten runs per cell, median reported.

80-94% less code, 47-77% less cost, and 3-6× faster than a no-skill agent, on every model. Every shortcut ponytail takes is marked in the code with a ponytail: comment naming its upgrade path. Reproduce it yourself: npx promptfoo eval -c benchmarks/promptfooconfig.yaml. Method and raw numbers: benchmarks/. Production-grade tasks, where an unconstrained agent bloats far more, are written up in benchmarks/results/.

How it works

Before writing code, the agent stops at the first rung that holds:

1. Does this need to exist?   → no: skip it (YAGNI)
2. Stdlib does it?            → use it
3. Native platform feature?   → use it
4. Installed dependency?      → use it
5. One line?                  → one line
6. Only then: the minimum that works

Lazy, not negligent: trust-boundary validation, data-loss handling, security, and accessibility are never on the chopping block.

Install

The most effort ponytail will ever ask of you:

Claude Code

/plugin marketplace add DietrichGebert/ponytail
/plugin install ponytail@ponytail

Codex

codex plugin marketplace add DietrichGebert/ponytail
codex

Open /plugins, select the Ponytail marketplace, and install Ponytail. Then open /hooks, review and trust its two lifecycle hooks, and start a new thread.

Pi agent harness

pi install git:github.com/DietrichGebert/ponytail

OpenCode

Run OpenCode from a checkout of this repo (the plugin reuses its hooks/ and skills/), and add to opencode.json:

{ "plugin": ["./.opencode/plugins/ponytail.mjs"] }

Injects the ruleset every turn at the active level; adds /ponytail and /ponytail-review. OpenCode also auto-loads this repo's AGENTS.md, so the rules hold even without the plugin. The plugin adds the lite/full/ultra/off levels.

That was it. He'd be proud. He won't say it.

Active every session. /ponytail-review finds what to delete in your diff. /ponytail ultra exists for when the codebase has wronged you personally. /ponytail-help explains the rest.

This fork adds three more. /ponytail-skill writes a new skill the lazy way — runs the ladder first and tells you when the skill shouldn't exist at all. /ponytail-claude-md updates CLAUDE.md without bloating it: every line is a per-session token tax, so it adds only what overrides a default and routes the rest elsewhere. /ponytail-critique audits a plan before you build it — keep / cut / shrink / defer verdicts on whether each piece is worth the code, the forward gate to /ponytail-review's backward one.

Context-engineering skills