Guards

Gives every agent that can edit a git worktree of its own, runs a project's setup script with its own port range, kills what an agent left running, removes an agent's worktree and branch once the session merges it, and tidies other merged branches on demand with /tidy

Jev gates Bash, Write and Edit, and screens Read and Bash results for injected instructions; a blocked command is held, for the person to run anyway or keep blocked

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

Hides secrets in tool results before Claude reads them: the secret values of every .env and .env.* from your session's folder up to the drive root, and anything that looks like a secret (KEY=VALUE under a secret name, passwords in URLs, private keys, JWTs, AWS keys, Kubernetes Secrets); tells Claude how to use them without printing them

Status line score 0-100 for how good a moment it is to /compact now, with reasons; offers a ready /compact that keeps goal, decisions, leftovers and paths, and adds that template to every compaction. Never compacts by itself.

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.

Redacts secrets and PII from every row Claude Code stores, before the model reads it and before the transcript keeps it. Reach L0: no network, no processes, no files.

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.

A knowledge graph across your Claude Code sessions. Each session records its topics and files; when another session covers the same ground you get an alert, and /graph can pull its findings into the one you are in.

Kessoku Ultimate Bocchi Theme: a Bocchi the Rock!-inspired charcoal-and-pink skin for all of Claude Code (an engine theme plus every render site), a live Kessoku Band panel with the band on stage as animated pixel-art sprites under spotlights and their subagents as songs on a setlist (solo any member) and band subagent types Claude can delegate to by name, and themed Cache Tax, Blast Radius...

Know whether your auto-memory index loaded whole. Reports the index's size against a limit you set at every session start, names the entries past the cut, and warns when a session pushes it over.

Enforce the style rules Claude keeps ignoring: banned words and phrases, a comment-density cap on added code, and files that must not gain comments. Rules live in .claude/style-cop.md and are both shown to Claude and enforced on edits.

A side panel that keeps what a conversation leaves open: questions, your tasks, findings and unfinished asks

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...

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.

Live mesh7 decisions, pending approvals and emergency stops in a pane

Verinoda in Claude Code: keeps the code index fresh while Claude edits, checks each edit for names that do not exist, reviews commits, lists what could be changed for you to choose (/verinoda-improve), and shows it all in a Turkish pane with an animated mascot.

A Claude Code mod: file paths in Claude's replies become links that open the file (or your editor at the line). macOS, Linux and Windows paths, relative ones resolved against the session folder.

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.

Verinoda in Claude Code: keeps the code index fresh while Claude edits, checks each edit for names that do not exist, reviews commits, lists what could be changed for you to choose (/verinoda-improve), and shows it all in a Turkish pane with an animated mascot.

Proposes the loose ends Claude leaves undone and lets you decide which to keep; keeps them in refs/loose-ends without touching your branches, and Chispa flags what needs your attention. English and Spanish.