caveman
claudeUltra-compressed communication mode. Cuts ~65% of output tokens (measured) by making the assistant talk like a caveman, without losing technical accuracy.
20 skills · 1 command · 3 agents · hooks
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Plugin ponytail from marketplace pip-boy in serban-marius/pip-boy. Commands read from the repo's manifest — 2 days ago.
ponytail-auditAudit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.
ponytail-debtHarvest every ponytail: shortcut comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.
ponytail-gainShow ponytail measured impact as a scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display.
ponytail-helpQuick reference for ponytail's modes, skills, and commands. One-shot display.
ponytail-reviewReview a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.
ponytailLazy senior dev mode for any coding task (write, refactor, fix, review): YAGNI, stdlib first, no unrequested abstractions. Not for non-coding requests.
Ultra-compressed communication mode. Cuts ~65% of output tokens (measured) by making the assistant talk like a caveman, without losing technical accuracy.
20 skills · 1 command · 3 agents · hooks
Keep GitHub quiet without you: pr-address-comments answers a PR's review feedback with evidence, pr-janitor decides which PRs need it, inbox-janitor cleans your notification inbox.
3 skills
Codebase reconnaissance agent and skills (recon, design-patterns) for exploring projects and applying GoF patterns
2 skills · 1 agent
G.O.A.T.: JIRA ticket to PR with a team of agents in TDD and two human gates (goat), plus pre-merge verdict and post-deploy regression watch (geiger)
2 skills
Mister Handy: the main session is HQ and orchestrates by default. A SessionStart hook marks HQ vs worker; HQ sends every substantive task out as a written brief to Orca worktrees, or to background subagents in git worktrees without Orca, then watches them through a STATUS file and acts when they finish, fail, ask or stall, without pulling transcripts back in. Briefs with runnable acceptance checks are routed (by rules, or by Jev when a key is set) to cheap workers (Claude haiku with only a Claude subscription, or pi on any inference provider) under a deterministic foreman that retries, climbs a model ladder and escalates to Claude.
1 skill · hooks
V.A.T.S.: verifiers by cadence as Claude Code hooks. Every edit -> lint + types on the one file; every git commit -> tests; failures go back to the agent. Plus on-demand mutation testing.
1 skill · hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Scaffold, validate, and publish new Claude Code plugins with proper structure
3 skills · 1 command · 1 agent
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.