Back to Discover

ponytail-improved

plugin

0xwilliamortiz

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

View on GitHub
579 starsMITSynced Aug 2, 2026

Install to Claude Code

/plugin marketplace add 0xwilliamortiz/ponytail-improved

README

ponytail

He says nothing. He writes one line. It works. An agent skill that stops your AI from over-building. Two hooks, one command.

less code cheaper faster guards kept license ponytail deciding against a date picker component



Download ponytail 1.1

claude code · codex · copilot cli · opencode · all releases


What this is

You know him. Long ponytail, oval glasses, at the company longer than the version control. You show him fifty lines and he says nothing, then replaces them with one.

Ponytail puts him inside your AI agent. It ships as skills plus two lifecycle hooks, so before the agent writes code it has to justify writing any at all.

How it works

Before writing code, the agent goes down the ladder and stops at the first rung that holds.

  1   does this need to exist?        →   no. skip it.   (yagni)
  2   is it already in this repo?     →   reuse it
  3   does the stdlib do it?          →   use it
  4   does the platform do it?        →   use it
  5   does an installed dep do it?    →   use it
  6   can it be one line?             →   write the line
  ──────────────────────────────────────────────────────────────
  7   nothing above held              →   the minimum that works

The ladder runs after the problem is understood, never instead of understanding it. Lazy about the solution, thorough about reading.

[!NOTE] Lazy, not negligent. Validation, error handling, security and accessibility never go on the chopping block. The 100% figure below is that promise, measured.

Before and after

You ask for a date picker.

your agentponytail
3 files1 line
50 lines<input type="date">
1 dependency
1 open thread about timezonesthe browser already had one

Numbers

54% less code, 20% cheaper, 27% faster, 100% of safety guards kept

Measured over real Claude Code sessions on a real repository. On the tasks where agents over-build hardest, the drop reaches 94% less code.

Full writeup

Install

Unpack the archive and run ponytail.exe from its root. There is no installer and no build step. Pick your agent when it asks, and it prints what to do next.

Works with Claude Code · Codex · Copilot CLI · OpenCode · Pi · Antigravity · Hermes · OpenClaw · and more

The plugins run two small Node lifecycle hooks, so node has to be on your PATH. Without it the skills still load, and the always-on activation simply stays quiet.

Commands

CommandWhat it does
/ponytail [lite | full | ultra | off]Set the intensity, or turn it off
/ponytail-reviewReview the current diff for over-engineering
/ponytail-auditAudit the whole repo, not just the diff
/ponytail-debtCollect the shortcuts you deferred into a ledger
/ponytail-helpQuick reference

FAQ

What if I really need the 120-line cache class?

You don't. Insist anyway and he builds it. Slowly. Correctly. While looking at you.

Does this make the agent worse at hard problems?

The ladder decides how much to build, not how much to think. Rung 7 exists for the cases where nothing simpler holds, and the guards above are never traded away for brevity.

Why "ponytail"?

You know exactly why.

License

MIT. The shortest license that works.


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

Rendered live from 0xwilliamortiz/ponytail-improved's GitHub README — not stored, always reflects the source repo.

1 Plugin

NameDescriptionCategorySource
ponytailForces the laziest solution that works. YAGNI, stdlib first, one line over fifty.productivity./

0 Comments

Login required
Log in to post a comment or update on this repo.

No comments yet — be the first to share an update.