BY HOOP.DEV / CLAUDE CODE PLUGIN

Hoop’s toolbelt,
now inside Claude Code

Guardrails, session risk analysis, token savings, and PII detection in one plugin install. Credential cloaking lands next.

Free & Open SourceUser-Level InstallNo Sudo
01

Add the marketplace

Run it once from any Claude Code session: terminal, desktop app, or IDE.

/plugin marketplace add hoophq/claude-marketplace
02

Install the plugin

Installs at the user level and follows you across every project and session. No per-repo setup needed.

/plugin install hoop@hooplabs
03

Guardrails apply immediately

Missing a binary? The plugin installs it on demand, with no sudo. Re-check anytime with /hoop:doctor.

🚧 fence guardrails active
hoophq / claude-marketplacePublic
Star

Hoop’s toolbelt for Claude Code: agent guardrails, credential cloaking, session risk analysis, token savings, and PII detection.

main8 items
$/plugin marketplace add hoophq/claude-marketplace
$/plugin install hoop@hooplabs
.claude-plugin/Plugin and marketplace manifests
commands/Slash commands (/hoop:doctor, /hoop:risk-report, /hoop:pii-scan)
hooks/Hook config wired into every session
scripts/Fail-open wrappers and the no-sudo installer
skills/Agent skills
docs/Guides
README.mdInstall steps and what is in the box
LICENSEMIT

Need to govern everything your AI agents are doing?

hoop enforces the same guardrails, credential handling, risk scoring, and data masking, but centrally. It covers every agent and every protocol, not just Claude Code sessions on one machine.