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 ivanshamaev/de-agent-skills --skill starrocks_memory_tuninggit clone --depth 1 https://github.com/ivanshamaev/de-agent-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/ivanshamaev/de-agent-skills/starrocks_memory_tuning)<a href="https://agentmods.dev/skills/ivanshamaev/de-agent-skills/starrocks_memory_tuning"><img src="https://agentmods.dev/badge/skills/ivanshamaev/de-agent-skills/starrocks_memory_tuning/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/ivanshamaev/de-agent-skills/starrocks_memory_tuning"><img src="https://agentmods.dev/badge/skills/ivanshamaev/de-agent-skills/starrocks_memory_tuning.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 | $0.08499 |
| Opus 5 | $0.00040 | $0.04249 |
| Sonnet 5 | $0.00016 | $0.01700 |
| Haiku 4.5 | $0.00008 | $0.00850 |
Grade C, and why
starrocks-memory-tuning scanned grade C with 2 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://<be_host>:8040/api/mem_tracker | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://<be_host>:8040/api/mem_tracker | python3 -m json.tool The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 967 lines · 80 tokens per session scan C b1e251fa9d90
starrocks-memory-tuning is a skill published in the GitHub repository ivanshamaev/de-agent-skills (18 stars, last pushed 3mo ago), with no licence file. It adds 80 tokens to every session and 8,499 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
troubleshooting-datavault4dbt
Diagnoses common datavault4dbt failures — satellites capturing too many or too few rows, multi-source high-water-mark issues, ghost-record/datatype errors, and YAML-metadata compile errors. Use when a datavault4dbt model errors on compile or run, a satellite detects the wrong number of changes, or a hub/link/satellite…
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…
byted-bytehouse-slow-query
A ByteHouse tool for finding slow database queries, examining how they run, and suggesting ways to improve them.
sap-background-jobs
Investigate SAP background jobs, including failed or aborted jobs, job status, job steps, job logs, runtime dumps, TBTCO, TBTCP, and TBTCJOBLOG0-9.
codex-log-guard
Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs2.sqlite, logs2.sqlite-wal, blockloginserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.