secret-guard
Stops a prompt that looks like it contains a secret, before it is sent.
sudipta26889Install
/plugin marketplace add sudipta26889/sd-claude-mods /plugin install secret-guard@sd-claude-mods
Run both lines inside Claude Code.
Hooks into
- Prompt
- Toasts
Also in sudipta26889/sd-claude-mods
-
deploy-guard
Holds a git push for your yes while a job is running, as your own check command defines one.
sudipta26889 in Git, updated
0
-
voice-fix
Swaps misheard words in a prompt using your own glossary. No model call.
sudipta26889 in Notifications, updated
0
-
reflect
Offers to save a correction such as "never do X" as a permanent rule, once you press Save. No model call.
sudipta26889 in Prompt, updated
0
-
handoff
/handoff summarises this conversation, saves it privately, and continues in a fresh one with the summary.
sudipta26889 in Prompt, 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