Panes

The Gobworks manager: browse every mod by category, see what each does and costs, turn mods and presets on or off, and check them. Best standalone in any terminal (gobworks); inside a running Claude Code session too (/mods).

A little game layer: 32 achievements for how you use Claude Code, with lifetime progress and a /achievements pane.

Something to do during long turns: /snake and /2048 in a pane, with high scores and a nudge when Claude is done.

Gob as a Tamagotchi-style companion who lives off your work: finished turns, green tests and commits grow him, and /pet lets you feed, play with, pet, nap and dress him. Free, and he never punishes you.

Jev (TypeSafe's System One model) as Claude's instant co-processor: bulk filter/classify/rank/semantic-grep tools, risk notes under permission dialogs, a check on unverified 'it passes' claims, and optional per-prompt effort.

Opt-in instant approval for clearly harmless shell commands: a strict pre-filter, then Jev classifies the command; only read-only inspection at ≥ 97% with no network risk skips the permission dialog. Every approval is logged.

No narrating comments: every comment an edit adds is judged by Jev in a few hundred ms; 'Added X as requested' and friends go back to Claude.

Instant repo-convention checks on every edit: CLAUDE.md, AGENTS.md, style guides and config facts compiled into atomic rules, each edit judged against all of them by Jev in a few hundred ms.

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.

Reflexes: short read-only requests (git status, diff stat, recent commits, cost, context) answered locally in an Express pane, no model turn.

A definition of done Jev checks after every turn: per-criterion probabilities that demand evidence, a band above the prompt, optional auto-continue.

Claude adapts to how you are doing: Jev reads each prompt's tone in a blink and, when the signal is strong, hands Claude one hidden line of guidance. Silent by default.

Notifications only when you are actually needed: after each turn Jev reads whether Claude asks you something, is stuck, or finished a long task; permission prompts ping too. Toast, chime, optional webhook.

A commit gate that reads the staged diff in a blink: Jev flags debug output, commented-out code, TODOs, machine paths, secrets and off-message changes before Claude's git commit runs.

"This helper already exists": new functions are compared against a git-grep symbol index, Jev judges the look-alikes in a few hundred ms, and Claude hears about duplicates.

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.

Jev ranks every file in the repo against each prompt in ~0.5 s and hands Claude the likely relevant ones (System-1 file triage).

An instant security reviewer on every code edit: ~20 yes/no checks per edit answered by Jev in a few hundred ms, fed back to Claude.

Catches tests being weakened to make them pass: every test-file edit is judged by Jev in a few hundred ms against what you asked for.

Jev notices when a prompt starts an unrelated task and offers a fresh conversation for it, saving context and prompt cache.

Every failed Bash/PowerShell command gets an instant Jev diagnosis (15 failure classes) and a playbook in this project's terms, as a note Claude reads.

Huge Bash/PowerShell outputs cut to the lines that matter: Jev scores every 12-line chunk against your request, the full log is saved for Claude to open.

Compaction without amnesia: archives the full transcript before each compaction and tells the summarizer to keep paths, decisions, preferences, TODOs and working commands.

What Claude touched this session: reads, edits (+/− lines), searches per file, main vs subagent, with flags for blind edits and repeated reads.