Makes your AI agent think like the laziest senior dev in the room. The best code is the code you nev
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you nev
He says nothing. He writes one line. It works.
~54% less code (up to 94%) · ~20% cheaper · ~27% faster · 100% safe
Measured on real Claude Code sessions editing a real open-source repo (FastAPI + React), against the same agent with no skill. ~54% is the mean across 12 feature tasks (Haiku 4.5, n=4); it reaches 94% where an agent over-builds (a date picker) and is near zero where the code is already minimal. ponytail keeps every safety guard while a bare "write one-liners" prompt drops one. (The earlier single-shot benchmark reported 80-94% as a flat figure; against a fair agentic baseline that is the per-task ceiling, not the average.) Full writeup · reproduce it.
benchmarks: preserve AISOP/AISP workflow entrypoints during Python cleanup
Pony
Pi: replacement systemPrompt can defeat structured prompt-section cache preservation
`hermes plugins install DietrichGebert/ponytail --enable` fails. wrong schema.
POSIX hooks error (exit 127) when Node.js is not on PATH — Windows variant is guarded, POSIX is not
Plugin fails to load on OpenCode v2: v1 plugin API (default export is a function, not an object)
Muse Code CLI
ponytail-help: Codex invocation should be $skill-name, not @skill-name
ponytail-debt: scan command doesn't skip .git or node_modules
OpenCode 2 support: plugin uses V1-only API, does nothing on V2