Documentation memory for AI coding agents—route project knowledge, reduce repeated context loading, and validate living Markdown docs.

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in your Obsidian vault, searches them with SQLite FTS5, and mines past transcripts automatically.

A build playbook that turns your coding agent into the foreman of a website build. It interviews you, forces the design and scope decisions, locks a visual system, writes the build brief, then verifies, ships, and indexes the site. Claude Code plugin and Agent Skill. Markdown only, no scripts.

Fill Claude Code's agent wait time with dev news — Hacker News, GitHub Trending & per-language sources in your status line, auto-translated with short summaries.

Marketplace of domain-specific plugins for AI agents (Cowork, Claude Code, OpenClaw). Build autonomous business workflows for finance, banking, legal operations, and sales using modular agent skills and commands.

Multi-plugin marketplace for Claude Code offensive security plugins

Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.

Unofficial community workarounds for Claude Code (empty thinking summaries; missing context-usage icon; no copy/paste of markdown).

Persistent memory system for Claude Code via Markdown. Setup with /init-project, resume with /catchup, wrap with /wrapup. Includes coding standards, MCP servers, and modular skills. Solves context loss after /clear.

Bootstrap a project with a Nurix harness — copies the harness's CLAUDE.md, skills, agents, rules, and hooks directly into the project from a bundled payload (no marketplace fetch, no network).