Bands

A side pane with robots: the main loop, every subagent and its tools, context, cost, rate limits and files touched

Shows the images you paste: thumbnails above the prompt, and larger pictures under each sent message in the chat; needs a kitty-graphics terminal such as Ghostty

Experimental kgai add-on for Claude Code with function hooks: checks each code-editing turn for a structural decision on the side, records it without a line in the transcript, and draws kgai's own tool calls as one line each. Requires the kgai plugin.

Session pane: context, cost and turns, the prompt cache with the time until it expires, keep warm and a guard that holds a prompt that would write an expired cache again, the last turn's tokens, cache, tools and refused calls, a task list Claude keeps with a switch that keeps Claude working while tasks remain open, an autopick switch that answers a question left unanswered with its recommended...

Test-first workflow for coding agents, without the spec ceremony. A PreToolUse hook keeps source edits behind a mirror test and protects existing assertions; the flow drives one vertical slice at a time, red to green, through the project's own gate. Ships its own tdd and grill skills; includes the Jev layer (model and effort routing, compaction, review) and the interface (usage row, gate...

RESCENE fan mod: WONI conducts while LIV, MINAMI, MAY and ZENA take the subagent and Orca worker tasks and report back, in Korean or English. 리센느 팬 모드: 원이가 지휘하고 리브·미나미·메이·제나가 작업을 맡아 보고한다.

Claude Code, with receipts. Plans with you, hands each task to a specialist agent, and keeps a session from calling work done until a verification is logged. Its hooks run in every session, a guard holds destructive shell commands for review, and setup can point your status line at OMCA.

Keeps a live local page for a long Claude Code task: what needs you, what was built, what was verified, and what was decided without you. Hooks record it without spending model tokens, the page follows light, dark or your system's setting, and when the task ends the same page is the report.

After a turn that edited files or ran commands, Haiku lists the choices Claude made that you did not state. Mark each right or wrong, add a note, and send the corrections back as one prompt. Starts off: /assumption-check on turns it on

An Enhance button above the prompt: Haiku rewrites your draft to name the skills that fit, the questions Claude should ask first and what done looks like. It never submits; Send does. Starts off: /prompt-enhancer on turns it on

Keep prompts aside as drafts of the session. End a prompt with ;; to save it instead of sending it, then /drafts to put one back in the prompt box.

Keeps long sessions going through API errors and rate limits: resubmits after a backoff when idle, waits out rate limits with a countdown, never loops, and stops the moment you type.

Every prompt you type gets a quiet second read: without changing your words, a hidden note gives Claude the goal in one line, the likely scope, the project's checks to keep green, and what done means. Haiku only for vague prompts; See, Undo and Off in the band.

Docs that went stale because of this turn's changes: changed names, flags, env vars and config keys are looked up in the docs, and Jev reads each section against the new code.

Keeps changes on task: every edit is judged by Jev against your last request (and Claude's plan) in a few hundred ms; drive-by changes go back to Claude.

Keeps credentials out of your code, your shell commands and Claude's context: blocks hard-coded secrets in edits, asks before commands with literal keys, redacts secrets from tool results and flags them in prompts.

Prompt cache status band (c / ctx / rwc / sc / plan limits) with hover help, cold-send guard, keep-warm, /board, /handoff that also picks up handoff files, and an autonomous mode that clears and continues each handoff. Fork of Cache Keeper by Nate Herk.

Keeps everything Claude writes in view and folds each stretch of tool calls and thinking between texts into one line you can expand

Makes past sessions recallable: indexes Claude Code and Codex transcripts, subagent runs, memory files, standing orders and second-opinion reviews into a local SQLite index (kept after Claude Code deletes old transcripts), gives Claude search, expand, recap and list tools, and adds /recall (search, last session, timeline, decisions, commands, files, PRs, ask), /remember, a...

Holds back a prompt that looks like it carries a secret (API keys, tokens, access-key pairs, private keys, passwords) before it reaches the transcript, puts it back in the box, and offers to save the secret as an env var in ~/.zshrc and send $NAME instead. No model calls.

Keeps a GitHub Spec Kit feature and its code tied together inside Claude Code: a new idea researched and shaped with you (or your PRD reviewed and cut into a roadmap), the spec in the system prompt, every edit booked against a task, a proof ladder per requirement, a local dashboard, and an autopilot gated by your decisions and the tests.

Steers every compaction, including automatic ones, with a brief that keeps goal, next step, files, decisions and state. Once context runs high, a button above the prompt runs /compact, so you compact before a long context eats into your usage limits and model performance.

Claude Code, played as an adventure: generative music that follows the agent's mood (/miod), a pixel knight who fights a monster for every edit and command (/knightod), and a transcript retold in a plain or game style (/scrollod). Each one turns on and off on its own.

Your project's everyday actions in a band above the Claude Code prompt: start the app, save to GitHub with Undo, pull, build, a knowledge graph and a typecheck that follow your work, and your usage limits.