Dry-runs risky Bash commands (recursive deletes, destructive git, kubectl delete, SQL wipes) and asks Proceed or Cancel first.
✳︎ blast-radius
└─ Make every conversation easier
Review tools for permission checks and sensitive data handling.
54 projectsDry-runs risky Bash commands (recursive deletes, destructive git, kubectl delete, SQL wipes) and asks Proceed or Cancel first.
Put API keys and other secrets into any config file without them appearing in chat, shell history or tool output.
A Claude Code plugin that, between configurable late-night hours, makes Claude extra cautious: risky Bash commands (deploys, force pushes, rm -rf, DROP/TRUNCATE) are held for confirmation, the system prompt gains a caution section, and a status line shows the active window.
The author nearly wiped a Kubernetes namespace after approving an agent’s `oc delete --all` without reading it, then built a suite of 11 Claude Code plugins using the new function hooks API. The main mod, guardrails, blocks destructive commands like mass kubectl/oc deletes, rm -rf, force-push, and secret reads, and tells Claude the user blocked it. Other mods cover activity monitoring, desktop notifications, context tracking, usage limits, prompt coaching, command discovery, and a mod manager. Nine of eleven never call a model, there is no telemetry, and the project is free and MIT licensed.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗Holds a risky shell command before Claude runs it, works out what it would change, and opens a pane with **Proceed** and **Cancel**. Cancel refuses the command and tells Claude why, so it knows nothing ran.
A Claude Code plugin that intercepts Bash tool calls and forces an explicit user dialog before any command that changes the machine (sudo, brew install, global config writes), even in auto mode, with per-project ask/block rules.
Masks secrets (API keys, tokens, passwords, private keys) in the Claude Code transcript; hover a masked value to reveal it.
Asks you before any package install (npm, pnpm, pip, uv, npx, winget and more) and shows a registry link for each package.
Track the scope of file edits using configurable thresholds, with model judgment and user overrides.

A Claude Code hook plugin that masks token-like strings in tool output before the model sees them.

Hide API keys and sensitive identifiers before tool results reach the model.
BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗Top 3 by votes, then GitHub stars
No. Votes and stars measure popularity. Review the source and permission scan before installing.