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 netdata/skills --skill troubleshoot-proxysqlgit clone --depth 1 https://github.com/netdata/skillsWrote 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/netdata/skills/troubleshoot-proxysql)<a href="https://agentmods.dev/skills/netdata/skills/troubleshoot-proxysql"><img src="https://agentmods.dev/badge/skills/netdata/skills/troubleshoot-proxysql/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/netdata/skills/troubleshoot-proxysql"><img src="https://agentmods.dev/badge/skills/netdata/skills/troubleshoot-proxysql.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 | $0.00081 | $0.02005 |
| Opus 5 | $0.00041 | $0.01002 |
| Sonnet 5 | $0.00016 | $0.00401 |
| Haiku 4.5 | $0.00008 | $0.00200 |
Grade A, and why
troubleshoot-proxysql 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 8d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshoot Proxysql
When to use this skill
- Backend Connection Starvation: Backend pool saturates. New queries queue or timeout.
- Multiplexing Collapse: Too many pinned sessions. Approaches 1:1 client-to-backend ratio.
- Monitor False Decisions: Health checks misconfigured. Backends flap between ONLINE and SHUNNED.
- Query Rule CPU Overload: Complex regex in
mysql_query_rulessaturates worker threads. - Configuration Drift: Changes not propagated between RUNTIME/MEMORY/DISK layers.
- Cache Stampede: Hot cache entry expires, thundering herd hits backend.
- Any time the user reports a Proxysql service behaving outside its expected envelope (elevated errors, latency, saturation, resource exhaustion, or unexpected restarts).
- An on-call engineer is paging on a Netdata alert tied to a Proxysql instance and wants a structured triage path.
Key facts
- This skill wraps the Netdata operator playbook for Proxysql. It does not replace the playbook; it routes a coding agent through MCP queries against the same signals the playbook relies on.
- ProxySQL is a high-performance MySQL protocol-aware proxy that sits between application clients and MySQL-compatible backends (MySQL, MariaDB, Percona). It is not a TCP relay; it fully parses the MySQL wire protocol and makes routing, caching, and connection management decisions per query.
- The playbook decomposes Proxysql health into 7 signal domains: Availability & Backend Health, Connection Management, Query Performance, Error Tracking, Traffic & Throughput, Resource Utilization. Each domain maps to one rule file in this skill.
- Dominant failure archetypes the playbook calls out: Backend Connection Starvation; Multiplexing Collapse; Monitor False Decisions; Query Rule CPU Overload; Configuration Drift.
- Netdata observes the signals listed in the rule files via its native collectors, plus any OpenTelemetry-shipped metrics that your Proxysql instrumentation adds. Both paths end at the same MCP query surface.
- Netdata's proxysql collector emits 40 context(s) under
proxysql.*. The rule files enumerate which contexts surface which domain; the Verification section below names the load-bearing ones explicitly.
What ships with it
9 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.
- README.md 89 B
- rules/availability-backend-health.md 6.0 KB
- rules/cluster-replication-integrity.md 4.2 KB
- rules/connection-management.md 6.2 KB
- rules/error-tracking.md 4.0 KB
- rules/other-contexts.md 3.8 KB
- rules/query-performance.md 5.1 KB
- rules/resource-utilization.md 6.2 KB
- rules/traffic-throughput.md 5.5 KB
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.
- 8d ago First seen · 164 lines · 81 tokens per session scan A 19feaf4f6392
troubleshoot-proxysql is a skill published in the GitHub repository netdata/skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,005 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
qdrant-monitoring-debugging
Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades without obvious config changes.
performance
Use when optimizing application performance — caching strategies, eager loading, query optimization, Redis patterns, or background job design.
perf-engineering
A guide to finding and fixing slow code, excessive memory use, slow startup, repeated database queries, and inefficient caching.
stale-derived-state
Diagnose a change that does not take effect until a reload, a logout or a navigation away and back, because a cache or a piece of derived state has no invalidation hook on write. Use when a save appears to work but the screen keeps showing the old value. Names the Crumbtrail queries that prove the write landed, and…
redis-observability
Redis observability guidance — which metrics to monitor (memory, connections, hit ratio, ops/sec, rejected connections), which built-in commands to reach for during incident triage (SLOWLOG, INFO, MEMORY DOCTOR, CLIENT LIST, FT.PROFILE), and when to use the Redis Insight GUI. Use when setting up monitoring or alerts…
performance-optimization-skill
Identify and fix performance bottlenecks — profiling, caching (Redis, CDN, memoization), bundle size, lazy loading, N+1 detection, memory leaks.