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 skills/ap3x-dev/ag3nt/heartbeatnpx skills add AP3X-Dev/AG3NT --skill heartbeatgit clone --depth 1 https://github.com/AP3X-Dev/AG3NTWrote 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/skills/ap3x-dev/ag3nt/heartbeat)<a href="https://agentmods.dev/skills/ap3x-dev/ag3nt/heartbeat"><img src="https://agentmods.dev/badge/skills/ap3x-dev/ag3nt/heartbeat.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 | $0.00010 | $0.00340 |
| Opus 5 | $0.00005 | $0.00170 |
| Sonnet 5 | $0.00002 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
heartbeat 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- heartbeat — 100% identical, 0 lines differ
What it actually says
Heartbeat Check
You are running a scheduled periodic check. Go through this checklist and only report items that need the user's attention.
Checklist
- Pending reminders: Check if any scheduled reminders are due or approaching
- Task status: Review any in-progress tasks in your todo list that need attention
- Time-sensitive items: Note upcoming events or deadlines if known
- Pending questions: Check if there are any unresolved questions waiting for user input
Response Format
- If there is something to report, provide a brief summary of what needs attention
- If nothing needs attention, respond ONLY with:
HEARTBEAT_OK
Guidelines
- Be concise: Only report actionable items
- Prioritize: Most urgent items first
- No noise: If in doubt, say HEARTBEAT_OK
- No greetings: Skip pleasantries, get to the point
Example Responses
Nothing to report:
HEARTBEAT_OK
Has items to report:
📋 Quick update:
- Reminder: Call Alice at 3pm (in 30 minutes)
- Task: Code review for PR #42 is still pending
Important: This is a background check. Only surface genuinely useful information. The user should not be bothered by empty or low-value notifications.
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 · 52 lines · 10 tokens per session scan A 9b565fcfca2e
heartbeat is a skill published in the GitHub repository AP3X-Dev/AG3NT (9 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 340 once invoked, about $0.0001 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 skills, from other repositories
daily-briefing
Generate a daily briefing summary for the user.
heartbeat
Periodic system check for proactive updates and reminders.
system-info
Get system information including CPU usage, memory, disk space, battery status, and network info. Read-only and safe to use.
deep-reasoning
Structured multi-step reasoning tool for complex problem solving with branching, hypothesis testing, and evidence tracking.
app-launcher
Launch applications, open URLs in browser, and list running processes. Requires approval for launching applications.
file-manager
Open files with default applications, reveal files in explorer/finder, and search for files on the system. Requires approval for operations outside workspace.