agentmods.dev

heartbeat-silence-check

heartbeat-silence-check is a skill for Claude Code, Codex from dailyaiagents-cpu/dailyai-os. It costs 72 tokens per session (710 once invoked), scanned A, original, MIT.

A scheduled check that watches whether a heartbeat file is still being updated. It treats an unchanged file for more than six hours as a sign that the heartbeat collector may have stopped.

In plain words
What is it for?
Use it to monitor the heartbeat collector, check the file’s age, and report green, red, or error states. It also supports custom time limits, quiet output, and dry runs that do not send alerts.
Why use it?
It catches silent monitoring failures that could leave system data stale without anyone noticing. It can raise a high-priority voice alert and Telegram message when the file is too old.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

not rated 0repo 6mo ago A scan 72 tokens original MIT

Good fit Use it to monitor the heartbeat collector, check the file’s age, and report green, red, or error states. It also supports custom time limits, quiet output, and dry runs that do not send alerts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check
View source ↗ dailyaiagents-cpu/dailyai-os
Install

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.

Any agent
npx skills add dailyaiagents-cpu/dailyai-os --skill heartbeat-silence-check
Clone the repo
git clone --depth 1 https://github.com/dailyaiagents-cpu/dailyai-os

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for heartbeat-silence-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check/github.svg)](https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check)
Your own site
<a href="https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for heartbeat-silence-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.00710
Opus 5.5 $0.00029 $0.00284
Sonnet 5.5 $0.00014 $0.00142
Haiku 4.5 $0.00007 $0.00071

Measured 2mo ago against content hash d4f07235d0f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

heartbeat-silence-check 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (run.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/heartbeat-silence-check/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

heartbeat-silence-check

A monitor-the-monitor. The heartbeat-collector writes workspace/system_memory/heartbeats.json every 15 minutes. When that write stops happening, the memory-sync audits silently report stale data forever. cont-14 found a 67-hour silence that 22 audits failed to escalate. This skill closes that gap by checking the file's mtime on a schedule and voice-alerting + Telegramming when it ages past 6 hours.

Procedure

bash skills/heartbeat-silence-check/run.sh

Exit codes:

  • 0: GREEN (mtime within threshold)
  • 1: RED (mtime exceeds threshold, alert fired)
  • 2: error (file missing / read failure)

Flags

  • --threshold-seconds N (default 21600 = 6h) — age past which RED fires
  • --dry-run — print the verdict, skip voice-alert + Telegram
  • --quiet — emit nothing on GREEN (default emits one-line status)

Silence-detector design choices

  • 6h threshold, not 1h — collector's own StartInterval is 15 min, so 4 misses = 60 min would be too tight. 6h is "definitely something is wrong, not a transient launchd hiccup."
  • High priority alerting — voice-alert priority=high (Daniel/200wpm)
    • Telegram priority=high. The whole point is to break through and notice. Low-priority would be the same failure mode this skill exists to fix.
  • No auto-revival — this skill is a detector, not a fixer. Cooper (or a follow-up ops session) decides whether to re-bootstrap the collector vs. dig in.
  • Skill, not Python — per CLAUDE.md "SKILLS NOT PYTHON" rule and P8 build-prompt-checklist. The detection is a 20-line bash; no daemon, no library — fits the skill mold cleanly.

Anti-runaway

If the silence-detector itself fires repeatedly (say, every 30 min for hours because the underlying collector is broken and Cooper is asleep), the alerts would become noise. Mitigation: a data/state/heartbeat-silence-last-alert timestamp file. Re-alert at most once every 6 hours after first RED. Once the collector recovers (mtime fresh), the timestamp file is deleted on the next GREEN run. This avoids the alert-storm pattern.

Read the full file on GitHub · 65 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2mo ago First seen · 65 lines · 72 tokens per session scan A d4f07235d0f4

Subscribe to this mod's changes

heartbeat-silence-check is a skill published in the GitHub repository dailyaiagents-cpu/dailyai-os (0 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 710 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

heartbeat-silence-check compared with skills from other repositories

heartbeat-silence-check next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
heartbeat-silence-checkdailyaiagents-cpu/dailyai-osSkill06mo agoMITA72Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code