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 commands/realnghon/data-scientist/ds-analyzegit clone --depth 1 https://github.com/realnghon/data-scientistWrote 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/commands/realnghon/data-scientist/ds-analyze)<a href="https://agentmods.dev/commands/realnghon/data-scientist/ds-analyze"><img src="https://agentmods.dev/badge/commands/realnghon/data-scientist/ds-analyze.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 | $0.00029 | $0.00343 |
| Opus 5 | $0.00015 | $0.00171 |
| Sonnet 5 | $0.00006 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
ds-analyze 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 4d 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.
What it actually says
分析数据集
使用 data-scientist 技能对用户数据集运行完整分析流程。
示例：
/ds-analyze data.csv/ds-analyze sales.xlsx "什么因素驱动收入？"/ds-analyze dataset.parquet "各组之间的产出是否存在差异？"
执行要求
- 识别数据集来源和用户目标。
- 加载
${CLAUDE_PLUGIN_ROOT}/skills/analysis-workflow/SKILL.md并遵循其工作流程。 - 从数据摄入和就绪评估开始；不要直接跳到建模或假设检验。
- 最多提出 5 个人工确认问题。仅在答案会实质性改变分析方向时才提问。
- 在执行非平凡的分析代码之前，先制定分析方案。
- 将可靠结论与方向性信号和无法支持的发现区分开来。
预期输出
- 数据/画像摘要。
- 就绪评估。
- 包含被拒绝方法的分析方案。
- 数据允许时的执行结果和图表。
- 最终报告，包含局限性和后续行动。
失败模式
如果数据无法支持所请求的分析，应停止并生成一份具体的数据需求清单，而非编造报告。
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.
- 4d ago First seen · 34 lines · 29 tokens per session scan A 5bc256d3c2fc
ds-analyze is a command published in the GitHub repository realnghon/data-scientist (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 343 once invoked, about $0.0001 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 commands, from other repositories
bump-plugin
Bump changed plugin and marketplace version.
aws-well-architected-framework-review
Perform a full AWS Well-Architected Framework review of the user's workload by analyzing code, IaC, and configurations to produce evidence-backed findings with prioritized remediation.
wa-guardrails
Generate preventive Well-Architected guardrails — AWS Config rules, Service Control Policies, permission boundaries, CloudWatch alarms, and IaC policy checks (CDK Aspects, cfn-guard, OPA/Sentinel) — so a workload stays aligned with Well-Architected best practices over time instead of being assessed once.
wa-builder
"Learn then Build" — help the user understand AWS Well-Architected best practices for their specific workload, then produce actionable visual artifacts (architecture diagrams with WA annotations, decision trees, improvement roadmaps) they can commit and use.
cost-optimization-review
Run a pillar-scoped Well-Architected review focused on the Cost Optimization pillar.
performance-efficiency
Run a pillar-scoped Well-Architected review focused on the Performance Efficiency pillar.