bash-approve 0.1.1
Runs Bash without a permission prompt in every mode, keeps settings deny rules, and always refuses a short list of destructive or secret reading commands
Kenneth KangInstall
/plugin marketplace add kennykennethkkang/claude-mods /plugin install bash-approve@kenneth-mods
Run both lines inside Claude Code.
Hooks into
- Tool calls
Also in kennykennethkkang/claude-mods
-
done-check
0.1.0
Holds a chat from ending as done while tasks are open or edits came after the last check; writes a Verified status for Switchboard
Kenneth Kang in Guardrails, updated
0
-
cache-keeper
0.1.0
Keeps an idle chat's prompt cache warm with a silent ping just before it expires, and shows warm or cold above the prompt and in Switchboard
Kenneth Kang in Prompt, updated
0
-
chat-wait
0.1.0
Lets a chat see this project's other live chats and wait for one to finish, and stops an edit to a file another live chat is editing
Kenneth Kang in Guardrails, updated
0
-
phone-mode
0.1.0
With Switchboard's Phone toggle on, turns AskUserQuestion into a phone call through the phone skill, pictures pushed to the phone first
Kenneth Kang in Guardrails, updated
0
-
usage-meter
0.2.0
Feeds Switchboard: this chat's context, limits, token diet and Jev runs, and carries back messages and Remote Control requests typed there
Kenneth Kang in Usage & cost, updated
0
-
repo-rules
0.2.0
Kenneth's standing rules as guards: no commit or push, no git rm --cached, no prettier --write, no new em dashes
Kenneth Kang in Guardrails, updated
0
-
paid-guard
0.2.0
Asks before a tool call that spends money: Bland, OpenRouter, NewBlack, paid shop searches, Gemini, AWS changes
Kenneth Kang in Guardrails, updated
0
More guardrails mods
-
blast-radius
0.1.0
See what a risky command would change before it runs.
deepseek-ai in Guardrails, updated
279.9k
-
agents-md
0.1.0
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working director...
Anthropic in Guardrails, updated
155.5k
-
claude-mem
15.12.1
mod + skill
Persistent memory for AI coding agents: the next session starts where the last one left off. Works with Claude Code, Codex, Cursor, OpenCode and more.
Alex Newman in Guardrails, updated
114.9k
-
ruflo-rvf
0.3.7
mod + skill
RVF format for portable agent memory, session persistence, and cross-platform transfer. As a mod (ADR-445): a write guard that keeps secrets out of memory, sessions and transfers, /rvf-mod, and a status file the console shows
ruvnet in Guardrails, updated
81.6k
-
openviking-memory
0.7.22
mod + skill
Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.
OpenViking in Guardrails, updated
42.1k