genshijin 原始人 🗿| Claude Code / Codex等AIエージェント 向け超圧縮コミュニケーションスキル。caveman の日本語版をベースに、日本語特有の冗長表現に最適化。

Keep Claude Code’s prompt cache warm during breaks and show the estimated cost before a cold send.

Skins for Claude Code: tool rows with icons, diff, table and Mermaid chart cards, a usage band and fifteen themes. /skin swaps them live.

Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations

Track the carbon footprint of your Claude Code sessions, in the terminal and the Claude desktop app

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

A port of opencode-buttplugio to Claude Code written by Opus 5.5.

jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones back next session.

Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.

A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.

TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI.

Claude Code mods: panes, bands, prompt guards, secret handling and memory tools

Local-first agent plan annotator

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works.

Track how much time you spend using Claude Code to AI-code

Vendor-neutral control-plane contract for coding agents: a normalized ToolCallEvent/Verdict schema with per-agent adapters (Claude Code, Codex, Amp, Gemini CLI) and a conformance suite.

Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.

Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.

A toolkit of skills, templates, and guides for bootstrapping AI-agent-friendly projects. Started from Anthropic's Claude Code engineering patterns, extended with a per-project self-improvement loop and more.

Agentic Software Engineering (ASE)

Learn as your AI coding assistant builds. You can outsource your thinking, but you can't outsource your understanding. A learning companion for the vibe coding era.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.