function-hooks

Community catalogue of public Claude Code mods (function hooks), scanned from GitHub with what each mod can read, write, run or send over the network. Browse https://mods.aidojo.si/

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

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.

NoPdb: Non-interactive Python Debugger

Ray Amjad's Claude Code mods: panes, bands, prompt guards, secret handling and memory tools. One marketplace, each mod installs on its own.

Claude Mods and the tools to build them: a builder skill, then mods

A rail of your Claude Code session's prompts: hover to read, click to jump (function hooks / Mods)

CoreHook Windows Function Intercept Module

Example managed and unmanaged plugins for CoreHook

Tool and library for hooking graphics APIs using CoreHook

Claude Code mod: context in tokens, 5-hour and weekly limits vs. the clock, prompt cache countdown, session cost and running agents, in one band above the prompt.

Claude Code mods that keep context use, plan quota and per-turn cost on screen, plus a guard that stops a session once it goes over budget.

Claude Code mods on demand — a skill that reads your conversation and builds the mod that fits: plan progress bar, files pane, context gauge, risky-command guard, test watcher. 11 tested templates, 29 building blocks, a map of 3,057 public mods. Terminal and desktop.

Markdown, painted onto Claude Code's prompt box as you type. Fenced code becomes a syntax-highlighted card before you even close the fence.

Claude Code mod (plugin) that adds a side pane with Activity, Files, Agents, Context and MCP tabs, a status line above the prompt, a restyled chat, Mermaid diagrams in the terminal, tables, and code and diff panels. Colours follow both /color and the /theme (dark, light and others).

Claude Code mod that draws Edit and Write diffs in two side-by-side columns

Voice coworker for Claude Code. Talk things through with a 3D wolf powered by ElevenLabs conversational AI; when you agree, it sends the prompt to Claude and speaks up when Claude is done.

Liquid-filled usage rings above the Claude Code prompt: 5h/7d limits, context, cache TTL, a fighter jet at high effort, and a pane of recent turns and costs.

Fireworks for Claude Code: every keystroke, tool call, commit and green test goes up in braille fireworks above the prompt. A Claude Code mod.

Claude Code mods that keep an agent honest — function hooks that guard scope, verify deploys, and draw the session above the prompt.