Guards

Wraps web, MCP and third-party tool output as untrusted data and defangs prompt-injection lines before the model reads them

A departure board for gh stack: live stack pane, a one-line status above the prompt, and raw force-pushes, rebases and PR base edits on stacked branches redirected to gh stack

Vets npm and PyPI packages before they install: blocks hallucinated, typosquatted and brand-new install-script packages, flags risky ones

A roguelike pane played by your real session: context is HP, errors spawn monsters, green tests slay them, commits open chests, PRs are floor bosses

Quietly enforces Paddy's writing rules: no em dashes in chat, files or outbound messages, and a nudge when replies run long.

Guards the 5h usage window: caps expensive-tier spawns per turn, keeps Fable spawns manual-only, draws a colour-coded usage gauge above the prompt (5h bar, reset time, turn burn, cache warmth, context size), and offers handoff + clear past a context size.

Toggle-able right sidebar for Claude Code: usage limits, context window, prompt-cache countdown, activity and touched files

Unofficial fan-made mod: before Claude edits a file, a ghost Clawd shows what happened to that file before (your past decisions, git history, your own past words) so settled choices don't quietly swing back. Not affiliated with or endorsed by Anthropic.

Learn while Claude works: short facts and yes/no questions in the band above the prompt, picked from what Claude is doing, paused whenever Claude needs you.

Project notes in .claude/notes.md: live dev servers, recent artifacts and pinned links, in a side panel and with /notes.

A development verification board: shows which tests, builds and type checks really ran, how they ended, and whether the result still matches your code.

Run each subagent on any model (gpt-6, grok-4.7, ...) at any reasoning effort, through model and effort parameters on the Agent tool

Side pane showing the files changed in this conversation as diffs; mark lines, comment, and send the comments back to Claude

Bento dashboard in the docked side pane: clock, context and compaction forecast, todo, git, Hacker News. Widgets on a pure contract.

Shows HTML files Claude writes (or /preview ) like a browser: terminal-browser when installed, else a built-in Chrome-rendered pane

Code review inside Claude Code: the branch diff in a pane, draft comments from you or Claude on any line, sent as a pending GitHub pull-request review. Needs Claude Code 2.1.287 or later, git and gh.

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

Draw a formula and show the PNG in a pane

What Claude is building (website, mobile app, desktop client, Unity game…), live in a panel of the client (desktop, mobile in Remote Control, terminal): Claude hooks up the project and the network bridge itself, and drives the same target as you

Don't reinvent the wheel: finds existing GitHub projects, MCP servers, skills and plugins that fit the conversation and shows them in a small pager above the prompt.

A pane listing figures, structures and data files written this session, with the notebook cell or script that made each figure and the data it reads

/tree: the project's directory tree in a side panel, with git change markers, refreshed as files change

A little protein in a side panel that folds a step for every finished run, and misfolds on failures

A pane and toasts for background shells, monitors and subagents: status, elapsed time, latest output line, exit code