Guardrails
208 mods. Block, rewrite or audit tool calls before they run.
- secret-guard 0.1.0 金鑰守門:遮蔽 prompt 和工具輸出裡的 API key,並擋下讀寫 .env、私鑰這類檔案;/guard 看狀態 0
- blast-radius 0.1.0 Holds destructive shell commands, shows what they would delete or overwrite, and asks Proceed or Cancel. 0
- session-journal 0.1.0 Writes a markdown log of every prompt, changed file and command to .claude/journal, with a /standup summary. 0
- secret-guard 0.1.0 Blocks reads of .env files and printing of API keys, with a red warning above the prompt. 0
- house-style 0.1.0 Enforces the no-em-dash rule: a system prompt section, a reminder to the model after a write that adds one, a toast when a reply uses one 0
- zsh-safe 0.1.0 Quotes glob flags zsh would expand (--include=*.ts) and keeps a grep that finds nothing from failing the command 0
- remote-guard 0.1.0 Asks before a destructive command runs on another machine over ssh (restarts, deletes, kills, reboots) 0
- dock 0.1.0 Container stacks per worktree: a pixel-art pane of every compose stack with its memory and worktree, orphans whose worktree is gone, and a guard that asks before booting another stack when memory headroom is low. 0
- tool-oneline 0.1.0 Folds tool calls in the scrollback into one line per call, or one line per run of calls, with no result block 0
- subagent-effort 0.2.1 Run each subagent on any model (gpt-6, grok-4.7, ...) at any reasoning effort, through model and effort parameters on the Agent tool 0
- blast-radius 0.1.0 See what a risky command would change before it runs. 0
- blast-radius 0.1.0 See what a risky command would change before it runs. 0
- review-lint 0.1.0 Hands Claude a cache-review checklist or test rules when an edit adds a cache or a brittle test assertion 0
- swamp 0.1.0 Gives Claude a tool that runs a swamp workflow and returns its result. 0
- slop-detector 0.1.0 Catches slop as Claude writes it: refuses a file edit that replaces code with a '... rest of the code' placeholder, and tracks TODO stubs, not-implemented throws, debug prints, @ts-ignore and other leftovers in a band above the prompt and a /slop pane. 0
- pin-everywhere Pinning a session turns on its Remote Control once machine-tag has put the machine icon in the title, so it shows by name and icon on every other computer and the phone; unpinning turns it back off 0
- html-shelf 0.5.1 终端里 Claude 的回复:.html 路径单击用浏览器打开;代码块画成带底色的卡片,一键复制;/open 打开最近的 HTML(Windows / macOS / Linux) 0
- ask-choice 0.1.0 返答に、選んで答えられる問いが文章のまま残っていたら、選択式の質問(AskUserQuestion)で聞き直させる 0
- blast-radius 0.2.0 Faengt gefaehrliche Shell-Befehle (Bash und PowerShell) ab, zeigt Befehl und Folge und fragt vor dem Ausfuehren nach; Standard aus, mit /ward fuer die Sitzung einschalten 0
- image-peek 0.1.1 Previews pasted images and images Claude sends, with Open and Reveal buttons (Explorer on WSL/Windows, Finder on macOS) 0
- context-saver 0.1.0 Refuses a main-agent Read over the token cap so a subagent reads the file and reports back. Reads its toggle and settings from agent-rules. 0
- agent-switchboard 0.1.0 Puts Claude Code sessions on Agent Switchboard: publishes each session's state as a snapshot file the board's hub reads 0
- lint-guard 0.1.0 An ordinary eslint wrapper: lints after every Write/Edit, a /lint command, and a band showing current findings. 0
- game-earcons 0.1.1 8-bit sound cues: a permission prompt or question waiting on you, a long turn finished, an error, a guard refusing a call, a save (macOS) 0
- pr-proof 0.2.5 mod + skill Shows the proof behind a PR under the reply that names it: checks, before/after screenshots, what was not checked, with Open and Reveal buttons 0
- guardrails 1.0.0 Stops risky shell commands before they run: killing ports owned by Docker containers, printing secrets from the environment, rewriting your kubeconfig, and asks before kubectl writes on production contexts. 0
- blast-radius 0.1.0 Before a shell command deletes or discards files, shows exactly what it would hit and waits for Cancel or Proceed. 0
- greve-generale 0.2.0 Les outils de Claude se mettent en grève au hasard, pour des raisons très françaises 0