safety-guard 0.1.0
Blocks risky actions before they run: recursive deletes of root or home, force pushes, pipe-to-shell installs, and writes to secret or key files.
Vaibhav WableInstall
/plugin marketplace add wablevaibhav/claude-mods /plugin install safety-guard@claude-mods
Run both lines inside Claude Code.
Hooks into
- Tool calls
- Toasts
- Slash commands
Also in wablevaibhav/claude-mods
-
task-progress
0.1.0
Always-visible progress band above the prompt: follows the todo list automatically, lets Claude report progress with a tool, and shows a live 'working' timer while a turn runs.
Vaibhav Wable in Usage & cost, updated
0
-
usage-dashboard
0.1.1
Claude usage dashboard pane (/usage-dashboard): 5h and weekly limit %, current and top model, pending / in-progress tasks, ETA and limit risk.
Vaibhav Wable in Usage & cost, updated
0
-
context-meter
0.1.0
Shows how full the context window is, warns at 70% and 90% so you can compact or start fresh before quality drops.
Vaibhav Wable in Usage & cost, updated
0
-
git-band
0.1.0
A one-line git status band above the prompt: branch, ahead/behind, staged, changed and untracked counts.
Vaibhav Wable in Git, updated
0
-
notes-todos
0.1.0
Your own persistent todo list and notes across sessions: /mytodo and /mynote, with an open-count in the status line.
Vaibhav Wable in Status line, updated
0
More guardrails mods
-
blast-radius
0.1.0
See what a risky command would change before it runs.
You in Guardrails, updated
247.7k
-
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
150.3k
-
ruflo-rvf
0.3.6
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
74.4k
-
openviking-memory
0.7.7
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
39.7k
-
tool-timing-badge
0.2.0
Times every tool call and wraps the engine's ToolUse rendering with a colored duration badge from the surface's own element table, on the terminal, Desktop and mobile. Hooks tool.call and ui.render using JSX.
claude-code-templates in Guardrails, updated
32.6k