ClaudeMap

Awesome Claude Code Mods

A nightly-scanned catalog of 50 Claude Code mods — function-hook plugins listed with each one's exact reach: what it hooks, what it can touch.

Plugins & Agentsmodsfunction-hookspluginscatalogsecurity
Visit projectkaranb192/awesome-claude-code-mods

A Claude Mod is a Claude Code plugin whose hooks are TypeScript functions running inside Claude Code's own process: they draw above the prompt, open panes beside the transcript, rewrite tool calls, spawn agents and touch the host — all with zero tokens. Anthropic proposed them as function hooks on 2026-09-03 and committed to shipping them on 2026-09-09; they remain early access, gated behind CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1, and the API can change between releases. This catalog's differentiator is the footprint column: every row records the events a mod hooks and the $ calls it makes, printed by Claude's own claude plugin validate before any mod code runs. A nightly scan clones every candidate repo on GitHub and refreshes the table, the badges and a generated scoreboard page. As of 2026-09-16, scanned against Claude Code 2.1.273: 50 mods in 121 candidate repos — 19 run host processes, 8 write files, 13 read files, 10 reach the network, 19 see every tool call, 15 see every prompt, and 2 fail to validate on this version.

What it does

  • Footprint per mod — events hooked plus $ calls — captured by claude plugin validate before any mod code runs
  • Reach levels quantified: L0 draws and remembers (16), L1 reads (4), L2 writes or runs (20), L3 network (10)
  • Nightly scanner clones all 121 candidate repos and refreshes tables, badges and the scoreboard page from the same data
  • Curated groups: dashboards and usage, while-you-wait, git/PR/CI, safety and privacy, memory and context, rendering, agents and workflows — plus a building-mods section

When to use it

Picking mods with eyes open about what each one can reach before installing; mod authors checking how their mod validates and which reach level it lands on; tracking a fast-moving new Claude Code capability.

Getting started

# reference catalog — browse on GitHub:
https://github.com/karanb192/awesome-claude-code-mods

# mods are early access; nothing loads without the flag:
CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1

Things to know

CC0-1.0. Mods themselves are early access behind an env flag and the API can change between releases — the catalog's own warning. Counts drift as the nightly scan reruns; the numbers here were stated as of 2026-09-16 against Claude Code 2.1.273. A footprint describes reach, not intent — L2/L3 mods still deserve a look at the code before you trust them.

Repository

karanb192/awesome-claude-code-mods

Charted

Related on the map

  • CometixCode

    Plugin / Agent

    An unofficial Rust 1:1 reimplementation of the Claude Code terminal UI, ported file-for-file onto an iocraft TUI framework.

    • terminal-ui
    • rust
    • reimplementation
    • unofficial
    View

  • Abide

    Plugin / Agent

    Hook-level enforcement for the natural-language rules in AGENTS.md and CLAUDE.md — every edit is judged and violations are repaired in the same turn.

    • hooks
    • code-review
    • rules
    • agents-md
    View

  • fast-jev-compaction

    Plugin / Agent

    A Claude Code plugin that replaces the lossy compaction summary with Jev-scored pruning: stale tool calls are dropped, and everything kept stays verbatim.

    • plugin
    • context-management
    • compaction
    • function-hooks
    View