Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/mergisi/openclaw-rules/heartbeat-configgit clone --depth 1 https://github.com/mergisi/openclaw-rulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/mergisi/openclaw-rules/heartbeat-config)<a href="https://agentmods.dev/rules/mergisi/openclaw-rules/heartbeat-config"><img src="https://agentmods.dev/badge/rules/mergisi/openclaw-rules/heartbeat-config.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00580 | $0.00580 |
| Opus 5 | $0.00290 | $0.00290 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
heartbeat-config scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Heartbeat & Scheduled Tasks
When configuring scheduled tasks for OpenClaw agents, use the cron jobs system.
Cron Jobs Configuration
Scheduled tasks live in ~/.openclaw/cron/jobs.json:
{
"version": 1,
"jobs": [
{
"id": "unique-uuid",
"agentId": "main",
"name": "Daily Morning Report",
"enabled": true,
"schedule": {
"kind": "cron",
"expr": "0 9 * * *",
"tz": "Europe/Istanbul"
},
"sessionTarget": "isolated",
"wakeMode": "now",
"payload": {
"kind": "agentTurn",
"message": "Generate the daily morning report. Include GA4 traffic, Stripe revenue, and top pages.",
"timeoutSeconds": 120
},
"delivery": {
"mode": "announce"
}
}
]
}
Common Cron Patterns
| Pattern | Schedule |
|---|---|
0 9 * * * |
Every day at 9:00 AM |
0 9,18 * * * |
Twice daily at 9 AM and 6 PM |
*/30 * * * * |
Every 30 minutes |
0 */2 * * * |
Every 2 hours |
0 9 * * 1-5 |
Weekdays at 9 AM |
0 9 * * 1 |
Every Monday at 9 AM |
Key Fields
- agentId: Which agent handles this job. Usually
"main". - sessionTarget:
"isolated"creates a fresh session. Use this for reports. - wakeMode:
"now"triggers immediately at scheduled time. - delivery.mode:
"announce"sends output to Telegram. - timeoutSeconds: Max execution time. 120s for reports, 60s for quick checks.
Best Practices
- Keep message payloads specific. "Generate report" is vague. "Run
node tools/ga4-report.cjsand send results" is clear. - Use
"isolated"sessions for scheduled tasks so they don't pollute the main conversation. - Set reasonable timeouts. API calls can be slow — 120s is safe for most reports.
- Always include timezone. Cron runs in UTC by default.
- Restart gateway after editing jobs.json:
openclaw gateway restart
Disabling Heartbeats
To disable all scheduled tasks, set heartbeat.interval: 0 in config.json and clear jobs.json:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 72 lines · 580 tokens per session scan A b0ace2de3212
heartbeat-config is a cursor rule published in the GitHub repository mergisi/openclaw-rules (2 stars, last pushed 6mo ago), licensed MIT. It adds 580 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
graphql
GraphQL: schema design, resolvers, performance.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.