Prompt

Classifies the user's prompt with Haiku against a few yes/no questions in one call and attaches a rough, non-binding hint for the main agent

Attaches a verification reminder to every delivery from another agent: a subagent's hand-back, a background task's notification, another session's message

Routes each turn to the cheapest capable Claude model using Jev, TypeSafe's decision model. Toggle with /route.

会話の最初のメッセージに現在ブランチ・git status・main からの差分コミットを注入する

dotfiles のガード群 (git 操作のスキル強制・ブランチロック・コメント規約・文脈注入)。機能ごとに hooks/ 配下の 1 ファイル

現在ブランチの OPEN PR を常駐監視し、CI fail / Copilot レビュー到着でセッションを起こす (pr-create の background スクリプト置き換え)

現セッションの scratchpad を Finder で開くボタンと /scratchpad コマンド

ship フローの状態機械をペインで可視化する。/ship-hud でトグル、進行中フローがあれば自動で開く。モデル向けに status ツールも提供

Lossless compaction for Claude Code: nothing is summarized; everything removed is archived verbatim with provenance and restorable by id (Jev or a local ruleset). /lossless to inspect and restore.

Experimental Jev-assisted model and effort selection for Claude Code: observe, pin, off, and opt-in auto.

After a deploy command succeeds, curls the live URL with cache-busting and puts the verdict in the model's context, so a deploy cannot be claimed without evidence.

After every Edit, Write, NotebookEdit or sed -i, a docked pane shows that file's uncommitted hunk with [keep] and [revert] buttons; a press dismisses or runs git checkout with no model turn.

Blinks the iTerm2 tab orange when a turn lands, for up to three minutes or until you type again, so a finished session is obvious from any other tab.

Denies a Bash merge (gh pr merge, git merge on main, push onto main) unless the latest human message says the word merge; ship, push and deploy do not count.

Keeps a per-turn tally of edits, runs, curls and destructive commands and shows it on the turn footer; a claim with no run flags the spinner, a destructive Bash unfolds its tool group, and an edit-without-run turn suggests running the tests.

Counts the distinct files a turn edits and stops at a threshold to make the goal get restated, so a small ask cannot quietly become a refactor.

3, 2, 1, GO above the prompt when you submit, a running gym clock while Claude works, and your split when the turn lands.

Every tool call your agent makes, checked before it runs. Verifies each pending tool call against the session's plan using TypeSafe AI's Jev model, then allows it, asks you, or blocks it.

A prompt typed while Claude is working is held in a stack above the prompt instead of landing in the running turn, and sent once the turn ends. Reorder the stack, edit a row in place, send one first, remove one, flush the lot. Needs function hooks (early access) and an interactive terminal.

Catch wild creatures above the Claude Code prompt: where your prompt leads (water, grass, fire, bugs, plans, builds) decides what appears. Pick a partner that draws under the logo, beside the spinner and above the prompt, and levels up and evolves as Claude works. Needs function hooks (early access) and an interactive terminal.

PII and secrets are swapped for placeholders (PII_PERSON_1) by regex and a local Gemma 4 before anything reaches Claude; placeholders are restored only where the work stays on this machine (local tool calls) and on screen.

Stretch breaks for people who live in Claude Code: the mascot acts out a stretch every few minutes, and every so many prompts it's pinky time, for the finger that hits Enter all day.

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

A council of independent code reviewers (Codex, Pi, Devin, OpenCodeReview) runs over your working diff in parallel; one summary of agreements, disagreements and unique findings. /council, plus an auto-review that only notifies.