A production-grade toolkit for detecting agent runtime anomalies and routing incidents through deterministic, approval-safe guardrails.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ops-detection-incident-routing
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ops-detection-incident-routing using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Ops Detection & Incident Routing?
The Ops Detection & Incident Routing skill is a specialized framework designed to bring reliability and safety to autonomous agent systems. Instead of relying on unpredictable, prompt-only monitoring, this skill provides a suite of bash and python-based tools to perform deterministic checks on local state and log files. It ensures that agent environments remain stable by monitoring for cron failures, context pressure, token spikes, and dangling sessions.
By leveraging this component of Openclaw Skills, developers can implement a controlled lifecycle for operational issues. The skill identifies runtime anomalies, applies in-flight and cooldown guards to prevent alert fatigue, and emits structured incident actions. This allows for a clean separation of concerns where automated detectors trigger specific investigator or remediator workflows within a safe, governed environment.
Ops Detection & Incident Routing Use Cases
- Monitoring autonomous agent environments for cron job failures or execution gaps.
- Detecting and managing resource spikes such as token usage or memory pressure.
- Implementing safety cooldowns and lock mechanisms to prevent redundant incident responses.
- Routing detected anomalies to specific investigation tasks with predefined severity levels.
- Maintaining a local, file-based state of incident history for auditability.
How Ops Detection & Incident Routing Works
- The threshold detector scripts parse local workspace logs, session snapshots, and cron states to identify triggers.
- Detected anomalies are logged as structured JSONL events, including severity levels and threshold metadata.
- The incident guard check verifies if a specific incident type is currently 'in-flight' or within a 'cooldown' period to avoid duplication.
- The incident router processes the alerts and determines the necessary action, such as spawning a new investigation task.
- State update scripts manage the transition of incidents from detection to remediation, updating the local state file accordingly.
Ops Detection & Incident Routing Setup
To get started with this skill, ensure you have bash, jq, and python3 installed. Follow these steps to initialize your environment:
# Navigate to the skill directory
cd ops-detection-incident-routing
# Run the setup script to check dependencies and create example scaffolds
bash scripts/setup.sh
You can then run a dry-run cycle to verify your configuration:
bash scripts/ops-detector-cycle.sh \
--workspace "$(pwd)/examples/workspace" \
--state-file "$(pwd)/examples/incident-state.json" \
--detector-out "$(pwd)/examples/ops-detector.jsonl" \
--router-out "$(pwd)/examples/router-actions.jsonl"
Ops Detection & Incident Routing Data Schema & Taxonomy
This skill utilizes structured JSON and JSONL files to maintain state and communicate between processes within the Openclaw Skills ecosystem.
| File Type | Format | Description |
|---|---|---|
| Detector Output | JSONL | Each line records a timestamp, status (OK/ALERT), and an array of triggered alerts. |
| Router Actions | JSONL | Defines actions like spawn or wait, specifying the task and severity. |
| State File | JSON | A persistent JSON object tracking the status and cooldowns of specific check_id entries. |
| Workspace | Directory | The target folder containing the logs and state files to be monitored. |
Ops Detection & Incident Routing Advanced Features
- Live Mode Support: Enables active locking and stateful incident tracking during execution cycles.
- Cooldown Guardrails: Prevents automated systems from entering infinite loops by enforcing mandatory wait times between remediations.
- Structured Incident Routing: Automatically converts low-level alerts into actionable investigator tasks for LLM-based agents.
- Local Scaffolding: Includes tools like
clean-generated.shto reset the environment state before new deployment cycles. - Deterministic Thresholds: Eliminates hallucination-prone monitoring by using shell-based logic for critical operational checks.
SKILL.md
Loading
Related Openclaw Skills
Smart Spawn API
A zero-plugin HTTP API that dynamically selects the most cost-effective and high-performing AI models for any specific task or sub-agent spawn.
Crypto & Stock Market Data (Node.js)
A professional-grade financial data integration for AI agents providing real-time crypto and stock market metrics without the need for external dependencies.
Model Router
Model Router is a self-aware routing engine for OpenClaw that dynamically matches specific tasks to the most capable and cost-effective AI models available in your configuration.
kk-daily-backup-report
A mobile-optimized reporting skill that provides concise, categorized daily backup status updates for servers and personal data.
Supabase REST Checkpointer
A durable LangGraph checkpointing solution that persists agent state via the Supabase PostgREST API without requiring a direct Postgres connection.
Website Flow Monitor
An automated system for discovering business-critical user flows and scheduling recurring synthetic health checks to ensure website uptime and functional integrity.
Featured*
