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 skills add dailyaiagents-cpu/dailyai-os --skill heartbeat-silence-checkgit clone --depth 1 https://github.com/dailyaiagents-cpu/dailyai-osWrote 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/dailyaiagents-cpu/dailyai-os/heartbeat-silence-check)<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.
<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>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 5.1 | $0.00072 | $0.00710 |
| Opus 5 | $0.00036 | $0.00355 |
| Sonnet 5 | $0.00014 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
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 12d 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 — 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.
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.
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.
- 12d ago First seen · 65 lines · 72 tokens per session scan A d4f07235d0f4
heartbeat-silence-check is a skill published in the GitHub repository dailyaiagents-cpu/dailyai-os (0 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 710 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…