Settings file Claude Code
Agent settings declaring 8 allowed tools.
2 7d ago A
tokens not measured
copy · 100% MIT
Instructions file CodexOpenCode
Instructions for tarunag10/ai-switchboard, covering rtk (rust token killer) - token-optimized commands, key commands, git (59-80% savings), files & search (60-75% savings) and test (90-99% savings) — shows failures only.
2 7d ago C 428 tokens
original MIT
Instructions file
Instructions for tarunag10/ai-switchboard, covering claude.md, coding profile, repo notes and style notes.
2 7d ago A 240 tokens
original MIT
Skill Claude CodeCodex
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find…
2 7d ago A 105 tokens
copy · 100% MIT
Skill Claude CodeCodex
Harvest every ponytail: comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or…
2 7d ago A 99 tokens
copy · 100% MIT
Skill Claude CodeCodex
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".
2 7d ago A 83 tokens
copy · 100% MIT
Skill Claude CodeCodex
Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
2 7d ago A 56 tokens
copy · 91% MIT
Skill Claude CodeCodex
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this…
2 7d ago A 100 tokens
copy · 100% MIT
ponytail
09Skill Claude CodeCodex
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports…
2 7d ago A 184 tokens
copy · 80% MIT