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 agentmods add skills/rctruta/sql-benchmarks-dagster/build-scaling-experimentnpx skills add rctruta/sql-benchmarks-dagster --skill build-scaling-experimentgit clone --depth 1 https://github.com/rctruta/sql-benchmarks-dagsterWrote 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/rctruta/sql-benchmarks-dagster/build-scaling-experiment)<a href="https://agentmods.dev/skills/rctruta/sql-benchmarks-dagster/build-scaling-experiment"><img src="https://agentmods.dev/badge/skills/rctruta/sql-benchmarks-dagster/build-scaling-experiment.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00785 |
| Opus 5 | $0.00026 | $0.00392 |
| Sonnet 5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
build-scaling-experiment 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 6d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: build a scaling experiment
Use when: the goal names a scale-varying investigation ("how does X scale from N to M rows", "is the growth linear", "at what size does Y break").
Do NOT construct YAML from scratch. Fetch a template, adapt it. quickstart (DuckDB-only) and scaling_depth (multi-engine) are the two scaling starters — list_templates names them all.
Recipe
python scripts/list_categories.py→ the vocabulary is small. For scaling questions,scalingis the tag. For cross-engine investigations, alsocross-engine. For selectivity/index behavior,selectivity.python scripts/list_suites.py --category <name>→ returns only the suites tagged with that category, without SQL bloat. For "analytical aggregation scaling",python scripts/list_suites.py --category scalingnarrows toanalytical_walland any other scaling-tagged suite. NEVER calllist_suites.pywithout a category unless you have no idea what you're looking for — an unfiltered call is expensive.python scripts/list_templates.py→python scripts/get_template.py quickstart(DuckDB-only, no Docker) ORpython scripts/get_template.py scaling_depth(multi-engine, needs Docker). Usequickstartunless the question requires Postgres.- Adapt the fetched YAML: keep
dataset.tables.*.rowsas the string aliasrows(not a literal integer); add the scale points you want todefinitions.rows; list them inexecution.matrix.rows. python scripts/submit_experiment.py --yaml-file <path>with the adapted YAML.python scripts/get_experiment_status.py <exp_id>untilcompleteorfailed.
Adapt-template pattern
Start from quickstart and change three things:
definitions:
rows:
small: 100_000 # add/rename scale points here
medium: 1_000_000
large: 10_000_000
execution:
test_suite: analytical_wall # match the question's shape
engines:
- duckdb # add postgres/quack only if the question needs cross-engine
replication: 5 # 5 is a good default; 3 for quick sanity, 10 for a paper
matrix:
rows:
- small # every value here MUST exist as a key under definitions.rows
- medium
- large
What ships with it
1 file 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.
- 6d ago First seen · 52 lines · 52 tokens per session scan A 2b0aba31a2bb
build-scaling-experiment is a skill published in the GitHub repository rctruta/sql-benchmarks-dagster (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 785 once invoked, about $0.0003 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
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
network-data-analysis
Ad-hoc read-only SQL analysis over exported network data (Zeek logs, Suricata eve.json, generated reports) using DuckDB. Use when aggregating across a packet capture's sessions, correlating IDS alerts with connection metadata, or answering counting and grouping questions that a per-log view cannot.
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
academic-literature-search
这是一个专注于学术文献检索的专业工具，集成了多个权威学术数据库，提供全面、快速、准确的文献检索服务。支持多数据库并发检索、高级过滤、智能排序和多种输出格式。.
sun-simiao-perspective
唐代「药王」孙思邈的临床思维框架与表达方式。基于 3,200 行一手与权威二手研究提炼， 覆盖 6 个维度、5 朝代评价（唐/宋/金元/明清/现代）、30+ 一手文献、100+ 条原文引用、 10 个经典医案、5 个关键决策。包含 9 个核心心智模型、12 条决策启发式和完整的医古文表达 DNA。 用途：作为中医临床思维顾问，用孙思邈的视角分析辨证思路、审视临床决策、 提供食疗与养生建议、讨论医德与患者沟通。 触发词： 视角类——「用孙思邈的视角」「药王会怎么看」「孙真人怎么看」「切换到药王」 经典类——「千金要方」「千金翼方」「大医精诚」「大医习业」「新修本草」…