Guards

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.

Hands the work to a fresh session before a long context degrades the model, and carries on there.

Nibbl: a tiny pixel pet above your prompt that nibbles your bugs

Holds risky shell commands (rm, git reset/clean/force-push, kubectl, terraform, docker, SQL and more), shows what they would change and whether you can undo it, and runs them only on your say-so.

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.

Run OpenAI Codex and Google Antigravity execution lanes from Claude Code with background event delivery, status tracking, and raw command protection.

Replaces the spinner with a tiny animated text-art scene of what Claude is doing right now: reading, searching, editing, running tests, waiting on you

Observe tool timing and outcomes without retaining arguments or output.

Spot tool calls above an elapsed-time threshold.

Count tool calls alongside the Claude Code spinner.

Manage AI agent skills (SKILL.md), playbooks and value chains: list, toggle, categorise, install from GitHub/monorepo/ZIP/local/marketplace, update, freeze, scan, export, index; run and organise playbooks; map skills and playbooks to value chains. Port of the Obsidian Skills Manager plugin plus BOB playbooks.

Starter mod: toast on start, status line counts tool calls

Band above the prompt: after a long run, which model and effort the main session, each subagent, Gemini and Ollama used

Band above the prompt: open questions Claude asked you plus bullets of what the last prompt did

Status line shows which model each running subagent is using

A Design workspace in Claude Code: see design options for a UI as images, select one, ask for more, ask for a change with a note and hand an option off to be built. Your agent runs the 12ui command line once per request, which draws every option at once with your own Codex sign-in.

Voiced pixel anime girls who roam the Claude Code transcript: they dance while Claude works and serve tea when it is done, and they do chores too: usage reports, a guard on dangerous commands, secret scans, quick code reviews and task recaps (/waifu help)

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

Provisions a temporary Boomi runtime in the session and hands its ID to Boomi Companion

Checks Boomi Companion's components against the team's standards before they are created, pushed or deployed

Mac notifications titled with the session name, saying what Claude needs from you: done, a question, or a permission. Works out of the box; install terminal-notifier (brew install terminal-notifier) to make notifications clickable, which brings you back to the app you were using.

Runs the project's linter after each edit and its type-checker before Claude stops, handing failures back to Claude

A right-hand sidebar of this session: files edited, recent commands, checks and denials, as a menu of tabs

Blocks catastrophic commands, asks before risky ones, and stops secrets from being written into files