dietrichgebert ponytail
COMMUNITYLABSCO SUMMARY
Six skills ship together, and the database marks all six "ready" — no paid account, no extra service, nothing beyond installing the plugin. ponytail itself is the ruleset: before touching code it walks a seven-rung ladder (does this need to exist, is it already in the codebase, does the standard library do it, is there a native platform feature, an installed dependency, can it be one line, only then the minimum that works), and it explicitly keeps validation, error handling, security, and accessibility off that ladder. The other five are single-purpose companions built on the same idea: ponytail-review and ponytail-audit look for over-engineering in a diff or an entire repository, ponytail-debt collects deferred-work comments into one ledger, ponytail-gain prints the benchmark numbers as a scoreboard, and ponytail-help is a reference for the rest.
It is aimed at anyone who has watched an agent reach for a library and a wrapper component to do what a native <input type="date"> already does, and wants a rule that catches that before the diff lands. The readme documents installation for roughly a dozen separate agent CLIs and harnesses beyond Claude Code — Codex, GitHub Copilot CLI, OpenCode, Gemini CLI, Devin CLI, Pi, Hermes, and others — which is unusually broad distribution for a repository this size.
READ THE FULL ANALYSIS
The headline number was revised down once, in public. An earlier single-shot benchmark reported 80-94% less code; a filed issue (#126) pointed out that its no-skill baseline pads answers with prose and options, inflating the gap. Measured again against a real agentic baseline — twelve feature tickets on a FastAPI-and-React template, Haiku 4.5, four runs each — the mean fell to about 54% less code, with cost down roughly a fifth and time down about a quarter, and ponytail was the only one of three arms tested that improved every metric while staying fully safe.
That number is still the maintainer's own measurement. We have not reproduced the FastAPI/React benchmark ourselves; the percentages above come entirely from the repository's own writeup and benchmark scripts, not an independent run.
One setup detail for two of the harnesses. The Claude Code and Codex plugins run their always-on activation through small Node.js lifecycle hooks; if node is not on the shell's PATH, the skills still work but that always-on trigger silently stays quiet instead of erroring.
ALSO IN THIS PACKAGE
ponytail
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
WHAT'S INSIDE
6 showing · 6 totalNothing else to set up — install it and go.
ponytail-audit
Reads the whole codebase looking only for over-building, then ranks what it finds — biggest saving first — as what to delete, what to shorten, and what a built-in feature already does for free.
ponytail-review
Checks one proposed change before it lands and says, one line per finding, what could come out and what should replace it — with the lines saved totted up at the end.
ponytail-debt
Every deliberate shortcut you flag with a comment gets pulled into one ledger, so a deferral can't quietly become permanent.
ponytail-gain
The project's own benchmark numbers as a scoreboard: how much less code got written, how much less it cost, and how much faster it ran across five everyday tasks.
ponytail-help
One card with everything needed to drive ponytail — its three intensity levels, the five companion skills, the command that switches between them, and how to turn the whole thing off.
ponytail
Makes an assistant code like a lazy senior developer: reuse what the project already has, reach for the language's own built-in tools next, and never build a piece of machinery until something actually needs it.
HOW TO GET IT
npx skills add dietrichgebert/ponytailnpx skills add dietrichgebert/ponytail --skill <name> --full-depthPick the skill name from the Skills tab — each entry there installs independently.
/plugin marketplace add dietrichgebert/ponytail/plugin install ponytail@ponytailTyped inside the agent's own prompt, not in a terminal. The marketplace is called ponytail, which is the part after the @.