loop-guard 0.1.0
Stops Claude when it repeats a failing command or rewrites the same file in a loop
tsnaketechInstall
/plugin marketplace add tsnaketech/claude-mods /plugin install loop-guard@claude-mods
Run both lines inside Claude Code.
Hooks into
- Prompt
- Tool calls
- Toasts
Also in tsnaketech/claude-mods
-
prompt-shortcuts
0.1.0
Slash-command shortcuts for prompts you type often
tsnaketech in Notifications, updated
0
-
token-usage
0.1.0
Band above the prompt showing 5-hour and weekly rate-limit usage
tsnaketech in Usage & cost, updated
0
-
bash-guard
0.1.0
Blocks destructive Bash commands and asks before risky ones
tsnaketech in Guardrails, updated
0
-
context-guard
0.1.0
Warns when the context passes 80% and offers to compact
tsnaketech in Guardrails, updated
0
-
focus-mode
0.1.0
/focus-dir <dir> restricts Claude's file edits to one folder
tsnaketech in Status line, updated
0
-
model-router
0.1.0
Sends short questions to a lighter model to save quota
tsnaketech in Notifications, updated
0
-
secret-guard
0.1.0
Blocks access to secret files and asks before commands that print secrets
tsnaketech in Guardrails, updated
0
-
sound-events
0.1.0
Notifies (bell or desktop) when a command is blocked or a question waits for you
tsnaketech in Notifications, updated
0
-
turn-notify
0.1.0
Desktop notification when a long turn finishes
tsnaketech in Notifications, 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
269.9k
-
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
154.3k
-
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
80.7k
-
openviking-memory
0.7.21
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
41.4k
-
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
33.1k