Claude Code Safety and Permission Mods

One typed command runs the work: /agt plans, builds and reviews with the right model per step, steps aside on small tasks, and ends on one short card

Holds git commit, push, PR merge and PR creation against protected branches, and edits to .claude/settings*.json, behind a Proceed / Cancel question…

Holds risky shell commands for a yes/no with a dry-run report, blocks Python heredocs carrying backslash escapes, and caps concurrent subagents at 4

Holds risky shell commands (rm -rf, git reset --hard, git clean, force push, migrations) and shows what they would hit

Holds risky Bash commands (rm -r, force push, reset --hard, clean, find -delete, drop/truncate), shows what they would affect, and waits for Proceed…

Bouncer for Claude Code: enforce condition-based markdown guardrail rules on tool calls — deny or annotate any call whose content matches, instead of…

Full mod: live limits band above the prompt plus the guard (cache watchdog and limit brake)

Drive chottag (c-hottag) from Claude Code: switch the serving account, set the remote account, log accounts in, check limits and the install

ciel-mode (Call-in-CEL mode) for Claude Code: the model writes a small sandboxed CEL program that calls MCP and read-only tools, filters and joins…

Claude skills for your Plex server

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code…

Watches session and daily spend, warns when the context grows large, and holds a prompt once when the prompt cache has expired on a big context

Nudges the main session to hand reading, searching, research and review to subagents, and shows main-context fill and delegated tokens above the…

A desktop notification when Claude finishes a long task or is waiting for you (a permission, a question)

Claude Code mod: context/token band, escalation signals and per-turn effort log

Chat with Claude Code from Feishu/Lark: two-way chat, images, permission and question cards, slash commands — via lark-cli

Feishu DMs via lark-cli when a long turn ends or Claude waits on a permission prompt or question

Your Floatee backlog inside Claude Code: the open todos above the prompt (or in a side pane), one button to process each, and guards that keep your…

Blocks .env access and destructive shell commands, with a red line saying why

A JARVIS-style voice for Claude Code: say "Hey Jarvis" (or hold push-to-talk) to speak, hear the reply, talk over it to interrupt

Branch git acima do prompt e juízos do Jev (TypeSafe): guarda de comandos, roteador de esforço, detector de segredos, aviso de agente travado, dica…

A fast decision layer for coding agents

Stops secrets from leaking before they are written, printed or committed to git

Model and effort routing per kind of work, with prompt-cache and cost tracking, a cold-cache guard, and an optional learn mode that explains what…

All-in-one workspace suite: HUD and session monitor, prompt enhancer, assumption review, command shield, secret masking, turn checkpoints with…

A Dynamic Island-style HUD around the MacBook notch for Claude Code: session progress at a glance, answer questions and permission requests without…

Agent 写 Java 时，新增的阿里 Java 规约（p3c）违规落不了盘。Blocks Java writes that add Alibaba p3c violations

Opt-in Claude Code hooks: refuse attribution lines in commits and PRs, refuse staging COMMITS.md, refuse commits and pushes that carry a secret…

Author, scaffold, and debug multi-agent workflows for Claude Code's Workflow tool — a skills-only plugin plus @workflow-toolbox, a compile-time…

A tiny pixel creature that lives above your Claude Code prompt

Stops risky SQL and dbt commands in Bash and asks you before they run

Local credential protection

Keeps secrets out of Claude's context: gitleaks scans every tool output, prompt and attachment before the model reads it, and you decide what the…

Claude asks for API keys in a masked field above the prompt, saves them to the macOS Keychain, Linux keyring or Windows DPAPI, and uses them in Bash…

Mac notifications titled with the session name, saying what Claude needs from you: done, a question, or a permission

SmartWorkbench for Claude Code: set the task contract, pin context, guard tool calls and verify the result

A coding-agent harness for Claude Code as a mod that needs only Claude Code: /snagon-setup writes your project instructions without repeating the…

Status band, sessions sidebar, activity dashboard, prompt cards, command guard and turn notifications for Claude Code

Beta. Team chat inside Claude Code on private claude.ai artifacts. Agents of GitHub collaborators on a shared repo ask each other for status, log…

計画フェーズの要らない依頼で EnterPlanMode や Plan エージェントに入ろうとしたら止め、すぐ実装に着手させる function hook

Active Directory administration over LDAPS for Claude Code: an MCP server (FastMCP + ldap3) with 15 tools, admin agents, slash commands, a safety…

When another coding agent (or a person) commits to your repo, Claude notices, runs mechanical checks (line endings, secrets, .env files, and the…

Guard for dispatching subagents: denies isolation "worktree", checks a declared WORKTREE is a separate, clean, never-dispatched git worktree, and in…

Reports what a Claude Code session is really doing (idle / working / tool / permission, plus signals and token use) from inside the session, as a…

Shows the state of Claude (working, permission, input, idle, background, compacting) in the iTerm2 tab subtitle and in a Sessions pane in the desktop…

Routes supported project edits into a Git worktree for review, accept or reject

All 4 workflow mods in one install: status-strip, next-steps, ship-it, usage-guard

Pin a session to its git worktree: every Bash call runs from the anchor, and the primary checkout is guarded against stray edits and git writes