The lazy senior dev, inside your agent. One line. It works.
A port of DietrichGebert/ponytail for the agentplugins CLI. All the rules, skills, and benchmarks live in the original — this is the plugin wrapper.
# install via agentplugins
pnpm dlx agentplugins install agentplugins-ponytail
# activate in session
/skill:ponytail| Rules | YAGNI-first coding philosophy; skips, reuses, stdlib, native, then writes minimum |
| Commands | /ponytail [lite|full|ultra|off], /ponytail-review, /ponytail-audit, /ponytail-debt, /ponytail-gain |
| Benchmarks | Real agent sessions on FastAPI + React, measured on LOC, tokens, cost, time |
Before writing code, the agent stops at the first rung that holds:
1. Does this need to exist? → no: skip it (YAGNI)
2. Already in this codebase? → reuse it, don't rewrite
3. Stdlib does it? → use it
4. Native platform feature? → use it
5. Installed dependency? → use it
6. One line? → one line
7. Only then: the minimum that works
Trust-boundary validation, error handling, security, and accessibility are never on the chopping block.
~54% less code on real tasks. Benchmarks, full methodology, and the full story: original README.
- Original project — full docs, benchmarks, all platforms
- Agent portability — which file maps to which agent
- Examples — real before/afters
MIT — same as the original.