merciagents/riphook
Deterministic security layer for Openclaw(Clawdbot), Cursor and Claude Code. Write secure code, prevent data exfil, and more
Intercepts tool calls, file reads, and outputs at the system boundary using deterministic hooks rather than prompts—blocking risky actions like secret exfiltration and dangerous shell commands regardless of agent intent. Emits agent-trace logs compatible with visualization tools, enabling audit trails of tool usage, human-agent collaboration, and failure points. Integrates via postinstall into Cursor, Claude Code, and OpenClaw, with static analysis feedback loops that enforce secure code generation by re-scanning edits until issues resolve.
Stars
44
Forks
1
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Feb 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/merciagents/riphook"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
23blocks-OS/ai-maestro
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph...
ImKKingshuk/LockKnife
LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI...
FlineDev/ContextKit
Claude Code context engineering & planning system for individual AI development workflows
backbay-labs/clawdstrike
Runtime security enforcement and threat hunting engine for autonomous AI fleets. Build Swarm...
conorluddy/ios-simulator-skill
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and...