DietrichGebert/ponytail

Caveman activates an ultra-compressed communication mode in Claude Code that cuts token usage by about 75% while preserving full technical accuracy. Use it when a user requests caveman mode, wants fewer tokens, or asks for brief responses.

Ponytail puts an agent into lazy senior developer mode that enforces YAGNI, stdlib-first, and minimal-diff choices for any coding task. Use it to write, refactor, fix, or review code without over-engineering.

Ponytail forces the laziest solution that actually works, favoring simplicity, the standard library, native platform features, and minimal diffs. Use it on any coding task to question scope, avoid over-engineering, and ship the shortest correct fix.

Ponytail Audit scans a repository for over-engineering and returns a ranked list of what to delete, simplify, or replace with standard library or native features. Use it before a code review to identify dead code, unnecessary abstractions, and duplicated platform functionality.

Ponytail Audit scans a whole repository for over-engineering and ranks findings—dead code, standard-library or native replacements, YAGNI abstractions, and shrink opportunities—so you can decide what to delete or simplify. Use it when asked to audit a codebase, find bloat, or identify removable complexity.

Ponytail Debt scans a codebase for `ponytail:` comments and reports them as a debt ledger, so deferred shortcuts are tracked instead of forgotten, and flags markers with no upgrade trigger.

Ponytail Debt scans a codebase for `ponytail:` comments and compiles them into a debt ledger, flagging entries with no trigger as rot risks. Use it when asked to list shortcuts or review what was deferred, as a one-shot report that changes nothing.

Ponytail Gain displays a plain ASCII scoreboard showing measured benchmark medians for lines of code, cost, and speed across five everyday tasks and three models. Use it to see the impact of the ponytail approach without editing files or changing modes.

Ponytail Gain displays a compact scoreboard of ponytail's measured impact: less code, less cost, more speed, using benchmark medians from five tasks and three models. Use /ponytail-gain to see savings and link to per-repo debt and audit commands.

Ponytail Help displays a one-shot reference card for ponytail's modes, skills, and commands. Use it to recall triggers, levels, configuration, and how to disable the lazy mode without changing state.

Ponytail Help displays a one-shot reference card for all ponytail modes, skills, and commands. Use it when you need to recall how to invoke ponytail lite, full, ultra, reviews, audits, and configuration options.

Ponytail Review reviews a code diff for over-engineering and flags what to delete: reinvented standard library functions, needless dependencies, speculative abstractions, and verbose code. Use it to keep changes lean and minimal.

Ponytail Review flags over-engineering in code diffs: dead code, reinvented standard library functions, unneeded dependencies, and speculative abstractions. Use it when asking for a simplicity review or 'what can we delete'.