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 resource-isolationgit 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/resource-isolation)<a href="https://agentmods.dev/skills/starrocks/starrocks-debug-skills/resource-isolation"><img src="https://agentmods.dev/badge/skills/starrocks/starrocks-debug-skills/resource-isolation/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/resource-isolation"><img src="https://agentmods.dev/badge/skills/starrocks/starrocks-debug-skills/resource-isolation.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 | $0.00080 | $0.05755 |
| Opus 5 | $0.00040 | $0.02877 |
| Sonnet 5 | $0.00016 | $0.01151 |
| Haiku 4.5 | $0.00008 | $0.00575 |
Grade A, and why
resource-isolation 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 9d 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://<fe_host>:8030/metrics?type=json" \ How it starts
The opening of the file, as written. The whole thing — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resource Isolation, Query Queue, and Query Governance
Investigation guide for resource groups, query queues, big-query circuit breakers, and SQL blacklisting.
Five root causes account for most resource isolation issues:
- Cause A — Unclassified queries monopolize resources (fall into
default_wg) - Cause B — Memory limit too tight causing disk spill and IO contention
- Cause C — Queue full causing immediate rejection (misleading error to client)
- Cause D — Big query unbounded for a specific user (no
big_query_*limits set) - Cause E — Statistics collection saturating BRPC worker threads
Metric Taxonomy — Read This First
Before diagnosing, understand the observable signals for resource isolation issues.
FE metrics
| Metric | Meaning |
|---|---|
starrocks_fe_query_resource_group |
Query count per resource group — which groups are being used |
starrocks_fe_query_resource_group_latency |
Percentile latencies per group — which groups have high P99 |
starrocks_fe_query_resource_group_err |
Error count per group — which groups are rejecting queries |
How to retrieve:
# All resource group metrics from FE
curl -s "http://<fe_host>:8030/metrics?type=json" \
| python3 -m json.tool \
| grep -A 5 "resource_group"
# Or raw metrics
curl -s "http://<fe_host>:8030/metrics" | grep resource_group
BE metrics
| Metric | Meaning |
|---|---|
starrocks_be_resource_group_cpu_limit_ratio |
CPU allocation ratio per group per BE node |
starrocks_be_resource_group_mem_limit_bytes |
Memory limit in bytes per group per BE node |
How to retrieve:
# BE resource group metrics
curl -s "http://<be_host>:8040/metrics" | grep resource_group
# Loop across all BEs
for be in <be1> <be2> <be3>; do
echo "=== $be ==="
curl -s "http://$be:8040/metrics" | grep resource_group
done
Query queue metrics
| Metric / Observable | Meaning |
|---|---|
query_queue_mem_used_pct_limit |
Memory usage threshold that triggers queuing |
| Queue depth in FE metrics | How many queries are currently waiting |
FE log query rejected: queue is full |
Queue at capacity — new queries rejected immediately |
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.
- 9d ago First seen · 583 lines · 80 tokens per session scan A 28a6615920d6
resource-isolation is a skill published in the GitHub repository StarRocks/starrocks-debug-skills (75 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 5,755 once invoked, about $0.0004 per session on Opus 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
doris-debug-resource-isolation
Use for Doris Workload Group / resource tag queue starvation, CPU/memory isolation leaks, and workload policy debugging. Commands: SHOW WORKLOAD GROUPS, EXPLAIN resource.
postgres-aiops
Use this skill whenever the user needs to operate or troubleshoot a PostgreSQL server/cluster as a DBA — a one-shot cluster health overview; server reads (version/uptime, settings, extensions, databases, roles); activity (sessions, idle-in-transaction, long-running queries, locks); query stats (pgstatstatements top-N…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
postgresql-indexing
PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing…
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
axiom-audit-grdb-performance
Use when the user mentions GRDB performance review, slow GRDB queries, app-group database setup audit, a ValueObservation that stopped updating, or pre-release GRDB scan.