All mods

5h and 7d limits of both cswap accounts in the band above the prompt

A live Codex session in a side panel: chat with it, pick model, effort and access; Claude and Codex message each other (the codex tool, @claude:), and Codex sees Claude's prompts, tool calls, replies and transcript.

Heaven's Feel cast for your agents: Sakura watches over the main session, Servants answer every subagent

Shows how long the prompt cache has left, next to the model name in the footer

Shows where the session's tokens go and when a fresh session would be cheaper

A labelled catalog of every place a mod can draw, every API it can call and every value it can read

Shows context, 5-hour and weekly limit usage in the band above the prompt

A pet that hatches from an egg and grows on the achievements you unlock while coding with Claude Code

Make file paths in Claude's replies clickable, opening the file in its default app

MYA: a voice for Claude Code on Linux/X11. Tap Right Ctrl to talk, Right Ctrl + Space to translate, and MYA answers aloud, with a ringing phone when it is your turn.

Plays Bad Apple!! in a pane or the band above the prompt, with sound

Band above the prompt showing prompt-cache age, hit rate, and a Compact button before the cache expires.

Rules for Claude Code alerts: when one is worth sending (done, blocked, error, usage limits) and where it goes (chime, macOS notification, ntfy, Slack, Discord or a JSON webhook).

Blocks destructive shell commands and access to secret files (.env, SSH keys, cloud credentials).

Catches API keys, tokens and private keys in the prompt you are about to send, and masks or blocks them before they reach the model.

A pane of this repo's latest GitHub Actions runs, refreshed while open

Ends every turn with the date, time, duration and tool call count

A tiny pixel creature that lives above your Claude Code prompt. It counts down your prompt cache and guards it on model switches, wakes Claude when your usage limit resets, brings a helper for every subagent, makes sound on Windows and Linux, yelps before risky commands, rolls its eyes at "You're absolutely right", and brings back your old /buddy.

Catches recurring agent failures from past transcripts: whole-disk find, foreground poll loops, errors masked by | tail, forgotten background shells

Shows spend in dollars for today and the month so far against a monthly budget, in the status line and /spend

A shared notes pane beside the conversation: capture, quote, and come back to what matters.

Denies a delegated agent lane any write to this repo's Claude settings files.

Report model drift and deny only positively invalid stale-pin launches.

Linear workflow for Claude Code: issue-next, issue-start, issue-review, issue-ship and issue-plan-cycle skills backed by a deterministic CLI, a linear-manager agent, and a mod that shows the current issue above the prompt with your other sessions and conflict warnings