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 StarRocks/starrocks-debug-skills --skill querygit clone --depth 1 https://github.com/StarRocks/starrocks-debug-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/starrocks/starrocks-debug-skills/query)<a href="https://agentmods.dev/skills/starrocks/starrocks-debug-skills/query"><img src="https://agentmods.dev/badge/skills/starrocks/starrocks-debug-skills/query/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/starrocks/starrocks-debug-skills/query"><img src="https://agentmods.dev/badge/skills/starrocks/starrocks-debug-skills/query.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 | $0.00073 | $0.07172 |
| Opus 5.5 | $0.00029 | $0.02869 |
| Sonnet 5.5 | $0.00015 | $0.01434 |
| Haiku 4.5 | $0.00007 | $0.00717 |
Grade A, and why
query scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://<be_ip>:8040/metrics" | grep "tablet_cumulative_max_compaction_score" How it starts
The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query Troubleshooting
Investigation guide for query hangs, slow queries, profile analysis, scan performance, join performance, and bug localization.
Three root causes account for the vast majority of cases:
- Cause A — Network/connection issue (TCP backlog, accept queue saturation)
- Cause B — FE lock / GC blocking (deadlock, full GC pause)
- Cause C — Scan bottleneck (data skew, no predicate pushdown, rowset accumulation)
- Cause D — Join bottleneck (broadcast OOM, missing statistics)
- Cause E — Bug localization (wrong results, executor crash)
Metric Taxonomy — Read This First
Before using any metrics, understand the two-layer observability structure:
FE-side metrics
| Metric / Field | Meaning |
|---|---|
fe.audit.log → QueryTime |
End-to-end wall clock time for the query (ms) |
fe.audit.log → ScanRows |
Rows scanned from storage layer |
fe.audit.log → ScanBytes |
Bytes read from storage layer |
fe.audit.log → MemCostBytes |
Peak memory allocated on FE side |
SHOW PROC '/current_queries' → QueryId |
Unique query identifier |
SHOW PROC '/current_queries' → ConnectionId |
Client connection ID |
SHOW PROC '/current_queries' → ScanRows |
Rows scanned so far (live) |
SHOW PROC '/current_queries' → ProcessRows |
Rows processed so far (live) |
SHOW PROC '/current_queries' → ExecTime |
Elapsed execution time (ms) |
SHOW PROC '/current_queries' → MemUsageBytes |
Current memory usage (live) |
Profile → OLAP_SCAN_NODE |
Per-operator timing; entry via SHOW PROFILELIST or FE HTTP UI |
BE-side metrics
| Metric / Field | Meaning |
|---|---|
starrocks_be_tablet_cumulative_max_compaction_score |
Max cumulative compaction score on this BE — high value means rowset accumulation, which inflates scan MERGE time |
Profile → MERGE (aggr/union/sort) |
Time spent merging rowsets at scan time; high = compaction lag |
Profile → IOTime |
Disk I/O time at storage layer |
Profile → JoinRuntimeFilterEvaluate |
Number of RuntimeFilters applied; 0 = no filter pushdown |
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.
- 1mo ago First seen · 715 lines · 73 tokens per session scan A 4a1c007ad1ba
query is a skill published in the GitHub repository StarRocks/starrocks-debug-skills (77 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 7,172 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
solr-query
To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.
hermes-mnemosyne
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMESHOME/plugins/mnemosyne/.
flux-query
Optimize slow database queries — analyze execution plans, add indexes, rewrite queries. Use when asked about "slow query", "optimize SQL", "query performance", or "explain this query".
data-data-virtualization
Use this skill when asked about data virtualization, Trino, Presto, Starburst, Dremio, query federation, federated query, cross-source join, pushdown, connector, or data lake query engine. This skill enforces: Trino/Presto architecture (coordinator/worker), connector patterns for query federation, query pushdown…
doris-debug-query
Use for Apache Doris slow/hanging/timeout queries. Covers FE planner (Nereids timeout), BE Profile bottlenecks, and Exchange WaitForData / brpc E1008 on port 8060. Session vars: enableprofile, querytimeout, nereidstimeoutsecond.
database-query
Natural language database queries with multi-database support, query optimization, and visual results.