- TESIGN / RADAR
- ponytail
ponytail
Make your agent write less code
WHO USES ITSolo developer · Team lead
For developers
Makes a coding agent ask whether the code needs writing at all.
139,398 stars · checked on GitHub GitHub check 30 h late · incl. +146 observed via GH Archive since then · 7-day +1,068 observed via GH Archive (as of )
RANKS All-time #15 Rising this week #5 AI #13 DEV TOOLS #2
RISING +133 ★ / 24h

TESIGN TAKE
The rule that matters: remove code that need not exist, but never cut validation, security or accessibility.
AT A GLANCE
- LICENSE
- MIT
- USAGE
- Use, change and redistribute, commercially too. Keep the notice.
- LANGUAGE
- JavaScript
- ACTIVITY
- last commit 2 days ago () · latest release v4.10.0 () · 16 releases
- COMMUNITY
- 65 contributors · 272 open issues (incl. PRs) · made by: an individual
- SOURCES
- GitHub
- OPEN SOURCE
- YES
- FIRST SEEN
- CATEGORY
- AI · DEV TOOLS
A summary, not legal advice.
WHY IT MATTERS
Hand work to a coding agent and abstractions and options nobody asked for tend to arrive with it. ponytail makes the agent behave like the laziest senior developer in the room, biasing it towards removing code that does not need to exist. It attaches as a skill or rule set to tools such as Claude Code and Cursor, under the MIT license.
BUILD FROM THIS
- A default agent configuration matching the team's coding rules
- A pre-review rule set that strips out the padding first
WHO IT'S FOR
- Solo developer
- the agent keeps adding abstractions nobody asked for
- Team lead
- wants a default rule that strips padding before review
START IN 5 MINUTES
# In the Claude Code prompt, as two separate messages:
# /plugin marketplace add DietrichGebert/ponytail
# /plugin install ponytail@ponytail
# Codex:
$ codex plugin marketplace add DietrichGebert/ponytail
$ codex plugin add ponytail@ponytailCAVEATS
- The Claude Code and Codex plugins need Node.js on PATH for their hooks
- On reasoning-heavy models such as GPT-5.5 it can cost more, per the README
- The savings figures are the repository's own benchmark
RECEIPT
- FIRST SEEN
- AT SOURCE
- KEPT
- STAR DELTA
- +133 ★ / 24h
- CREATED → FIRST SEEN
- 93d
- WHEN FIRST SEEN
- 136,829 ★
- SOURCES
- GitHub
The same facts in machine-readable form — View as Markdown · JSON
SIMILAR TOOLS
Up to five from AI by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation.
| IMAGE | NAME | ★ TOTAL | ▲ 7d | LICENSE | PLATFORM | LAST PUSH |
|---|---|---|---|---|---|---|
![]() | eccSkills, memory and security for agents | ★ 259k | ▲ +832 | MITpermissive | windows · macos · linux · cli | |
![]() | Hermes AgentSelf-improving personal agent | ★ 246k | ▲ +375 | MITpermissive | linux · macos · windows · android · cli | |
![]() | DeepSeek HarnessPlugin agent harness for developers | ★ 225k | ▲ +1,356 | MITpermissive | web · cli | |
![]() | ponytailMake your agent write less codeTHIS ENTRY | ★ 139k | ▲ +1,068 | MITpermissive | — | |
| mattpocock/skillsCARD | ★ 261k | ▲ +872 | MITpermissive | — |
TIMELINE
- Repository created
- FIRST SEEN BY TESIGN







