Prevent context overflow with automatic session truncation and memory preservation. Never lose important conversations again. Features: token-based trimming,...
Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2)
Validate Moltbook API requests before sending. Checks required fields (content, title, submolt), warns about incorrect field names (text vs content), prevents failed posts and wasted cooldowns. Use be
Maintain persistent focus on active work with hierarchical task tracking. Prevents the agent from forgetting mid-project context, drifting between topics, or...
Prevent sessions.json bloat from accumulating isolated sessions (hooks, crons, subagents). Sets up a cron to archive stale sessions to daily JSONL files and...
Secret redaction MCP server for OpenClaw agents. Prevents API keys, DB credentials, SSH keys, emails, IPs, JWTs, and 29+ other secret types from leaking to L...
Proactive session capacity monitoring and management for OpenClaw. Prevents context window lockups by warning at configurable thresholds (75%, 85%, 90%, 95%)...
Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities. Invoke for authentication, authorization, input validation, encryption, OWASP Top 1
When building OpenClaw agents that read untrusted text, use this skill to prevent prompt injection and memory poisoning. Standard utility for secure memory o...
Intent inference and alignment for persistent AI agents. Classifies gaps between tasks and intentions, checks for misalignment before executing, and prevents...
IoT monitoring simulation to predict CO2 tank depletion and prevent weekend gas outages in cell culture facilities. Monitors cylinder pressure, calculates co...
Output validation gates for AI agent systems. Prevents hallucinated data, leaked internal context, wrong formats, duplicate sends, and post-compaction drift....
Hardens API endpoints against common attacks. Covers rate limiting, input validation, auth, CORS, headers, injection prevention, error handling, and monitoring.
Prevents your AI from breaking code by revealing hidden file dependencies through git forensics.
Complete customer success, retention, and expansion revenue system. Use for churn prevention, health scoring, onboarding optimization, QBR preparation, expan...
Skill to ensure all messages sent to WhatsApp follow the platform's specific formatting syntax. It prevents markdown bloat and ensures a clean, mobile-first reading experience.
Scans installed or remote OpenClaw skills for security risks like credential leaks and suspicious code to prevent supply chain attacks.
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-sui...
Prevent context loss during LLM compaction via Write-Ahead Logging (WAL), Working Buffer, and automatic recovery. Three mechanisms that ensure critical state...
Monitors AI agents in real-time to detect anomalies and enforce safety policies with automatic emergency shutdown to prevent damage and cost overruns.
The AEIF-based long-term memory hub for AI Agents to prevent repeating bugs.
AGENTS.md/IDENTITY/SOUL/USER periodic reload skill to keep context fresh (.md-only v1.1.2). Prevents confusion and forgetting in long sessions. Edit HEARTBEA...
Implements Silviu-specific guards and runbooks to enforce validation, prevent common errors, and manage browser and GitHub interactions in OpenClaw.