Mirrors ios-dock and swift-design-lint state into a file Holdout.app shows on the Touch Bar
✳︎ holdout-bridge
└─ Make every conversation easier
Claude Code mods, plugins, skills, hooks, status lines and MCP servers. Browse community builds with original sources and L0–L3 permission levels.
556 projectsMirrors ios-dock and swift-design-lint state into a file Holdout.app shows on the Touch Bar
Long-term memory plugin for coding agents with typed, scoped facts and Claude Code hooks.
A community-built searchable directory and plugin marketplace for Claude Code mods: 67 plugins from 35 repos installable via /plugin marketplace add omarcevi/claudemods, with commit pinning, weekly version bump reviews and clean-config install testing.

BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗Stops Claude adding banner, multi-line, long or narrating code comments

Keeps Claude Code's conversation clean, and puts the details to the side
Introduces the new mods capability in Claude Code, which allows features to be built directly into Claude Code, and suggests having the agent first analyze repetitive issues in its own workflow before deciding whether to solve them with a mod, hook, skill, or settings change.

firstmate-calm
Claude Code plugin showing plan usage limits, context fill and session cost on a quiet line above the prompt, with yellow/red threshold alerts at 50%, 80% and 95% that reset each limit period.

Claude Code adds mods functionality, allowing customization of behavior and interface with a few lines of TypeScript, installed as plugins via /plugin, built on hooks; Anthropic says /diff and AGENTS.md support are built with mods.

Claude Code now lets you change Claude Code. Mods are small JavaScript or TypeScript files, packaged as plugins, that run inside your session. They can draw new UI, rewrite prompts, and step into tool calls.
▶ ♫Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗A Claude Code mod that displays context token usage and session cost above the prompt, and asks the agent to flush notes before auto-compaction.
Masks secrets (API keys, tokens, passwords, .env values) in tool output and prompts before Claude reads them