Rogue Security AIDR — real-time AI agent detection and response for Claude Code
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Real-time AI agent detection and response (AIDR) for Claude Code. Observes every prompt, tool call, permission request, and subagent — flags prompt injections, secret exfiltration, and destructive commands before they reach production.
One-line installer (recommended):
curl -fsSL https://raw.githubusercontent.com/qualifire-dev/rogue-install/main/install.sh | bash
The installer downloads this plugin into Claude Code's plugin cache, enables it
in ~/.claude/settings.json, and writes credentials to ~/.rogue-env.
Manual install (inside Claude Code v2.1+):
/plugin marketplace add qualifire-dev/rogue-plugin-claude
/plugin install rogue@rogue-marketplace
/rogue:setup
Get an API key at https://app.rogue.security/settings/api-keys.
.claude-plugin/plugin.json — plugin manifest
hooks/hooks.json — 14 command-based lifecycle hooks
commands/setup.md — /rogue:setup slash command
commands/status.md — /rogue:status slash command
scripts/setup.sh — credential storage helper
SessionStart, UserPromptSubmit, PreToolUse, PostToolUse,
PostToolUseFailure, PermissionRequest, Stop, SessionEnd,
SubagentStart, SubagentStop, InstructionsLoaded, ConfigChange,
Elicitation, ElicitationResult.
All hooks are type: "command". They source credentials from /etc/rogue/env
(system-wide, for MDM) or ~/.rogue-env (per-user) at runtime, then POST the
event payload to https://api.rogue.security/api/v1/hooks/claude.
If ROGUE_API_KEY is empty, hooks return {} (allow) — fail-open by design,
so Claude Code never hangs on Rogue infrastructure issues.
| Command | Purpose |
|---|---|
/rogue:setup | Walks through API-key entry, identity detection, and credential storage |
/rogue:status | Pings the API, fetches active rulesets, shows mode + actor identity |
Credentials live in one file: ~/.rogue-env (mode 600). Hooks source it
on every fire — no shell-rc patching, no environment leakage to other tools.
export ROGUE_API_KEY=rsk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
export [email protected]
export ROGUE_ACTOR_NAME='Your Name'
System-wide MDM deployment can drop the same exports into /etc/rogue/env —
hooks check that path first.
To revoke: rm ~/.rogue-env (per-user) or sudo rm /etc/rogue/env (MDM).
Prepend rgx! to any prompt to allow it through and mark the previous
detection as a false positive in the dashboard. Per-prompt only.
https://app.rogue.security/aidr
curl on PATH (every hook uses it)Proprietary. Copyright © Qualifire, Inc. All rights reserved. See LICENSE.
npx claudepluginhub qualifire-dev/rogue-plugin-claude --plugin rogueHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
affaan-mComplete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
xu-xiangEfficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains
rand