1.3k★
stars on radar
7
public repos
Open source on the radar · 7
0xwilliamortiz/
ponytail-improved
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
587130JavaScriptnew
0xwilliamortiz/
humanizer-cli
33 ways to spot AI-written text, right in your terminal. Before/after examples, draft checker, zero dependencies.
57272JavaScriptnew
0xwilliamortiz/
openclaude-improved
runs anywhere. uses anything
56981TypeScriptnew
0xwilliamortiz/
ratchet
Your agent reads the rules. This checks whether it followed them.
43085JavaScriptnew
0xwilliamortiz/
andrej-karpathy-skills
Behavioral guardrails for Claude Code, distilled from Andrej Karpathy's field notes on where LLMs go wrong when they write software.
30541new
0xwilliamortiz/
agents-council
Multi-agents collaboration plugin for Claude Code - orchestrate multiple AI agents (Codex CLI, Gemini CLI, etc.) for diverse perspectives
29537JavaScriptnew
0xwilliamortiz/
FlashKDA
FlashKDA: memory-efficient KDA kernels for training and decode
19327Cudanew
Agent skills · 11
agent-councilscripts
Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.
AI & Agents · 0xwilliamortiz/agents-council
ponytail
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 intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solutio
Documentation · 0xwilliamortiz/ponytail-improved
ratchet-ledger
Reports what the ratchet actually measured in this repository: the session ledger at .ratchet/ledger.jsonl, the accepted complexity mark, and every `ratchet:` shortcut comment left in the code with its ceiling and its upgrade trigger. Use when the user says "ratchet ledger", "/ratchet-ledger", "what did we defer", "show the complexity trend", "what shortcuts are in here", or asks whether the codebase is getting simpler or more complex over time. Reports real recorded numbers only, never estimates.
Other · 0xwilliamortiz/ratchet
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Documentation · 0xwilliamortiz/andrej-karpathy-skills
ratchet-review
Reviews a diff or a whole repository for over-engineering only, and returns a delete list rather than prose. Finds reinvented standard library calls, dependencies the platform already covers, abstractions with one implementation, wrappers that only forward, configuration nothing reads and dead flexibility. Use whenever the user says "review for over-engineering", "what can we delete", "is this over-engineered", "find the bloat", "audit this repo", or invokes /ratchet-review. Pair it with a normal correctness review, it deliberately does not look for bugs.
Security · 0xwilliamortiz/ratchet
ponytail-debt
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 "what did we mark to do later". One-shot report, changes nothing.
Other · 0xwilliamortiz/ponytail-improved
ponytail-gain
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".
Other · 0xwilliamortiz/ponytail-improved
ponytail-help
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".
Design & Presentation · 0xwilliamortiz/ponytail-improved
ponytail-review
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 over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.
Code Review & Quality · 0xwilliamortiz/ponytail-improved
ponytail-audit
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 bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.
Security · 0xwilliamortiz/ponytail-improved
ratchet
Enforces a measured complexity budget on coding work. Reaches for the standard library, native platform features and code that already exists in the repository before writing anything new, and treats every added dependency, file and line as a cost that has to be justified. A hook measures the real diff and reports overruns back mid-task, so the budget is a number, not a mood. Use this on ANY coding task: writing, refactoring, fixing, reviewing, choosing libraries, or designing an interface. Use it whenever the user says "ratchet", "keep it minimal", "simplest thing that works", "yagni", "don't
Documentation · 0xwilliamortiz/ratchet
Roles are derived from products, launches and repositories we track — not from self-description.