Zylos is open-source infrastructure that gives an AI agent persistent memory, scheduled activity, communication channels, and the ability to maintain and extend itself. Individuals and teams use it with Claude Code or Codex through Telegram, Lark, or a web console. Its catalogue add-ons define settings, instructions, and skills for operating the agent.
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 zylos-ai/zylos-core --skill health-checkgit clone --depth 1 https://github.com/zylos-ai/zylos-coreWrote 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/zylos-ai/zylos-core/health-check)<a href="https://agentmods.dev/skills/zylos-ai/zylos-core/health-check"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/health-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/zylos-ai/zylos-core/health-check"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00518 |
| Opus 5.5 | $0.00015 | $0.00207 |
| Sonnet 5.5 | $0.00008 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
health-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 24d 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.
What it actually says
System Health Check
Periodic system health check delivered via the C4 Control queue.
When to Use
- Receiving a control message with "health-check" in the content
- The activity monitor enqueues this automatically at regular intervals
Steps
1. Check PM2 Services
node ~/zylos/.claude/skills/health-check/scripts/pm2-snapshot.js
The helper parses pm2 jlist internally and prints only the allowlisted health
fields (name, status, pid, and restart_time). Never run or print raw
pm2 jlist output because it contains each process's inherited environment.
Every service should have status: "online".
Record which services are stopped or errored.
2. Check Disk Space
df -h / /home 2>/dev/null || df -h /
Thresholds:
- OK: < 80% used
- Warning: 80-90% used
- Critical: > 90% used
3. Check Memory
free -m
Thresholds:
- OK: < 80% used
- Warning: 80-90% used
- Critical: > 90% used (or swap > 50% used)
4. Report Results
If all checks pass, log to ~/zylos/logs/health.log:
[YYYY-MM-DD HH:MM:SS] Health Check: PM2 X/X online, Disk XX%, Memory XX% - ALL OK
If any issues found, notify whoever is most likely to help:
- Check your memory files for a designated owner or ops person
- If none designated, notify the person you normally work with most
- Use
c4-send.jswith the appropriate channel and endpoint to send the alert
Issue Resolution
| Issue | Action |
|---|---|
| PM2 service stopped | pm2 restart <service> and report |
| High disk usage | Check logs directories, report findings |
| High memory / swap | Report findings, check for runaway processes |
What ships with it
4 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.
- 24d ago Changed · +3 lines 2dfbeaabf8de
- 2mo ago First seen · 73 lines · 38 tokens per session scan A 9a5fb2624933
health-check is a skill published in the GitHub repository zylos-ai/zylos-core (1,160 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 518 once invoked, about $0.0002 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 2026-08-30.
health-check compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| health-checkzylos-ai/zylos-core | Skill | 1.2k | yesterday | MIT | A | 38 | Claude Code |
| cloud-image-bakeopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 27 | Claude Code, Codex |
| cloudflare-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 72 | Claude Code |
| gcloud-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 55 | Claude Code |
| vercel-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 59 | Claude Code |
| aws-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 59 | Claude Code |
| ov-server-operatevolcengine/OpenViking | Skill | 42k | yesterday | AGPL-3.0 | A | 39 | Claude Code, Codex |