Guards

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

The review gate as a tool.check function hook. Every shell call is decided in process, so the non-commit calls -- almost all of them -- cost no subprocess at all, and a blocked commit can be put to you as a question instead of refused outright. The decision itself is still bin/review-gate, run only for a command that mentions a commit, so both routes read the same receipts and cannot disagree.

Switches the Claude in Chrome extension between named browser profiles with select_browser, which needs no approval click, and picks the default before the first browser call of a session.

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.

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.

Routes heavy Bash commands (test suites, builds, Docker) to a second machine over ssh, with the PATH export and working directory already right, and the commit synced first.

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.

A pixel-art Ragtag athlete above the prompt who does a rep every turn: the session is an AMRAP of thrusters, burpees and pull-ups.

Jev-scored context pruning for Claude Code through OpenRouter: at compaction every tool call and result is scored by TypeSafe's Jev decision model, stale ones are dropped or truncated, everything kept stays verbatim. An optional gate truncates oversized tool outputs as they arrive.

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 pane beside the transcript with the GitHub pull requests and issues related to the current session: drag a title or description to leave a comment on it, add as many as you like, then Submit sends them all as one prompt. Watch each pull request's checks, review decision and mergeability update on a timer.

An unofficial fan-made pixel cat that lives in the band above the prompt and reacts to what Claude is doing: thinking, editing, craning after a search, yowling in a shell, squeezing its eyes shut at a tool error, and folding its ears down to sleep between turns.

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.

Lossless context compaction for Claude Code: old tool output moves to local files and comes back unchanged by id, or by what it is about with a Jev key.

Subagent monitor: a live band above the prompt for running agents, and /sub: this session's subagent history with alerts (file conflicts, stalls, tier mismatches, denied calls), a detail page per agent (select a row, Enter), a cost estimate, and an in-panel settings page (/sub set), in a band above the prompt or a side pane.

Switch between saved Claude logins and watch every account's rate limits

A workspace pane for Claude Code: agents and worktrees, checkpoints, notes, changes and memory files in one tabbed pane

The sessions you are working in right now as small cards above the prompt: a status lamp, a short label, what just happened, and one press to answer or jump there.

Dispatch Pilot：一个在 Claude 之外的决策模型（Jev 或 Clef，二选一）在你每次发消息时决定主 agent 这一轮的 effort，每一步都按这一档发出，一轮进行中每隔几步再判断一次；也为主 agent 派出的每个 agent 和 Workflow 脚本里的每个 agent 按 Artificial Analysis 的基准选模型和 effort（sonnet 和 opus 至少 medium）。主 agent 的模型从不改变，prompt cache 不受影响（只在 Claude Code 订阅下成立；Bedrock、Vertex 和网关上切换 effort 会让缓存失效）。它还不让主 agent 读完整的 skill 列表，改为在你发消息时推荐合适的几个，一轮中途主 agent 可以用 find_skill 工具查 skill。agent...

Tracks a task through Matt Pocock's idea-to-ship flow, shows the next step above the prompt, and holds a build until its checks prove it.

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.

Always-on status line and a pane for this session's Bash calls, background tasks and Codex/Pi/Devin/OpenCodeReview runs: elapsed time, output freshness, verdicts and errors.