# Send ReefWatch to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "reefwatch",
    "name": "ReefWatch",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/yasnaak/reefwatch",
    "canonicalUrl": "https://clawhub.ai/yasnaak/reefwatch",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/reefwatch",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=reefwatch",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "CHANGELOG.md",
      "CONTRIBUTING.md",
      "README.md",
      "SKILL.md",
      "manual_scan.py",
      "pyproject.toml"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "reefwatch",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T12:16:18.957Z",
      "expiresAt": "2026-05-06T12:16:18.957Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=reefwatch",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=reefwatch",
        "contentDisposition": "attachment; filename=\"reefwatch-1.3.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "reefwatch"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/reefwatch"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/reefwatch",
    "downloadUrl": "https://openagent3.xyz/downloads/reefwatch",
    "agentUrl": "https://openagent3.xyz/skills/reefwatch/agent",
    "manifestUrl": "https://openagent3.xyz/skills/reefwatch/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/reefwatch/agent.md"
  }
}
```
## Documentation

### What it does

ReefWatch is a lightweight host-based intrusion detection system (HIDS) that runs as a background daemon on the same machine as OpenClaw. It continuously monitors the local system for security threats and alerts the user through OpenClaw's messaging channels ONLY when something suspicious is detected.

### Architecture

ReefWatch runs as an independent Python process (not consuming LLM tokens) and communicates with OpenClaw via the local webhook endpoint (/hooks/wake) to alert the user.

[Collectors] → [Detection Engines] → [Alert Manager] → [OpenClaw Webhook] → [User]

### Detection Engines

YARA: File and process scanning for malware, webshells, miners, ransomware
Sigma: Log-based detection for brute-force, privilege escalation, lateral movement
Custom Rules: System-specific checks (file integrity, process anomalies, network connections)

### Start monitoring

When the user asks to start ReefWatch or enable security monitoring:

Verify dependencies are installed:
pip3 install -r ~/.openclaw/workspace/skills/reefwatch/requirements.txt --quiet



Download initial rulesets (first time only):
python3 ~/.openclaw/workspace/skills/reefwatch/setup_rules.py



Start the daemon:
nohup python3 ~/.openclaw/workspace/skills/reefwatch/reefwatch_daemon.py \\
  --webhook-url "http://127.0.0.1:18789/hooks/wake" \\
  --webhook-token "${OPENCLAW_HOOKS_TOKEN}" \\
  --config ~/.openclaw/workspace/skills/reefwatch/reefwatch_config.yaml \\
  > ~/.openclaw/logs/reefwatch.log 2>&1 &
echo $! > /tmp/reefwatch.pid



Confirm to the user: "🪸 ReefWatch is now active. I'll alert you if any threats are detected."

### Stop monitoring

kill $(cat /tmp/reefwatch.pid 2>/dev/null) 2>/dev/null && rm -f /tmp/reefwatch.pid

Confirm: "🪸 ReefWatch stopped."

### Check status

if kill -0 $(cat /tmp/reefwatch.pid 2>/dev/null) 2>/dev/null; then
  echo "ReefWatch is running (PID: $(cat /tmp/reefwatch.pid))"
  tail -5 ~/.openclaw/logs/reefwatch.log
else
  echo "ReefWatch is not running"
fi

### View recent alerts

tail -20 ~/.openclaw/workspace/skills/reefwatch/alert_history.jsonl | python3 -c "import sys,json; [print(json.dumps(json.loads(l),indent=2)) for l in sys.stdin]"

### Update rules

python3 ~/.openclaw/workspace/skills/reefwatch/setup_rules.py --update

### Run manual scan

When the user asks to scan a specific file or directory:

python3 ~/.openclaw/workspace/skills/reefwatch/manual_scan.py --target <path>

### Alert Format

When ReefWatch detects a threat, it wakes OpenClaw with a message like:

🔴 REEFWATCH ALERT
━━━━━━━━━━━━━━━━━━
Type: Brute-force SSH attempt
Severity: HIGH
Source: auth.log
Detail: 47 failed login attempts from 192.168.1.105 in 2 minutes
Rule: sigma/ssh_brute_force
Time: 2026-02-22 15:43:21
━━━━━━━━━━━━━━━━━━

Forward this alert to the user immediately through their active messaging channel. If the user asks for more details, check the full log at ~/.openclaw/logs/reefwatch.log.

### Important Notes

ReefWatch does NOT consume LLM tokens while monitoring. It only triggers OpenClaw when alerting.
On macOS, some collectors require granting Full Disk Access or specific permissions.
YARA scanning can be CPU-intensive; default config scans changed files only, not full disk.
The daemon auto-recovers if a collector fails; it logs the error and continues with remaining collectors.
All data stays local. ReefWatch never sends system data to external servers (only to OpenClaw's local webhook).
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: yasnaak
- Version: 1.3.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-29T12:16:18.957Z
- Expires at: 2026-05-06T12:16:18.957Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/reefwatch)
- [Send to Agent page](https://openagent3.xyz/skills/reefwatch/agent)
- [JSON manifest](https://openagent3.xyz/skills/reefwatch/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/reefwatch/agent.md)
- [Download page](https://openagent3.xyz/downloads/reefwatch)