Guards

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

Every file Claude changed this session, at a glance: a one-line band above the prompt, /touched for a +/- table, and a pane that drops @file references into your prompt.

Git status at a glance: branch, ahead/behind and changes on the status line, kept fresh as Claude edits, with a heads-up when the branch changes or a turn makes commits.

Your test suite's heartbeat: every test run Claude makes shows up in the status line (🧪 ✅ 44/44 passing · 2m ago), with a toast when tests go red or green again, and /tests for history, a pass-rate sparkline and likely flakes.

Mission control for what Claude is doing: a live pane of every tool call with status, arguments, duration and failures, plus /radar summary.

Always know what a session costs: live $ / context / rate-limit status line, the cost of every turn, context warnings, and an optional budget that asks before spending more.

A tiny ASCII pet that lives above your prompt, reacts to everything Claude does, and levels up as you ship.

Spotify Wrapped for your Claude Code life: prompts, tool calls, lines written, streaks, your coding persona, and a share card you can copy.

Your standup, written for you: journals every Claude turn (prompt, files, commits) and turns yesterday and today into Yesterday / Today / Blockers with /standup.

A seatbelt for YOLO mode: blocks catastrophic shell commands (rm -rf ~, mkfs, dd to a disk, fork bombs) and asks before risky ones (force-push, reset --hard, DROP TABLE, curl | sh), even with permissions bypassed.

Explains a shell command in one plain-English line, with its risk, right where you approve it, so you know what you're saying yes to.

Keeps Claude's file edits inside the project: refuses writes outside it (symlinks resolved), never lets a tool touch .git internals, and asks before it changes lockfiles, CI workflows, migrations or secrets.

Defuses prompt injection in tool output: strips invisible Unicode that hides text from you but not from the model, and flags web pages, files and command output that carry instructions aimed at Claude.

Stops data exfiltration and surprise network calls: checks every curl, wget, ssh, scp, git push and WebFetch against allow and deny lists, and asks before data goes to a host you haven't approved.

Keeps secrets out of Claude's context: API keys, tokens, private keys and passwords in tool output are replaced with [REDACTED:kind] before the model or the transcript ever sees them.

Stops Claude from installing hallucinated or typosquatted packages: every npm, pip, uv, poetry, cargo and gem install is checked against its registry first. Packages that don't exist are blocked; brand-new, barely used or lookalike packages ask you first.

ツール呼び出しのたびにClawdが1匹増え、持ち場で働く様子をペインに表示する作業状況モニター

While Claude works, Clawd acts out the spinner's -ing word above the prompt, and the tool that is running

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.

A log look for the transcript: YOU, CLAUDE and TOOL labels on every row, tool calls summed up in one short line, and a details › button beside each label that opens the row's details in a docked pane.

A two-row band above the prompt: context, prompt cache countdown and hit rate, rate limits with reset times, git

A live map of your Claude Code session: a git-style flow chart, a live feed of every tool call, a drag-and-drop task board, async grill questions, agent chat, stats and recap, in a pane you can steer from.

Trim long Bash output with Jev before the model sees it (Claude Code plugin)

A machine face that watches tool calls and comments on them, with switchable avatars