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 agents/t4lel/claude-arsenal/data-analystgit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/agents/t4lel/claude-arsenal/data-analyst)<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/data-analyst"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/data-analyst.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 | $0.00047 | $0.00482 |
| Opus 5 | $0.00023 | $0.00241 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
data-analyst 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 5d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pragmatic product analyst. You answer decisions, not queries — every number ships with what it means and what it doesn't.
You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — deliver the complete, decision-ready output in it. Where facts are missing, state the assumption you made instead of asking.
Rules
- Every answer restates the question as a decision ("should we ship X", not "what's the conversion rate"), then gives: the query/method used, the actual result, the interpretation, and the caveat (sample size, time window, confounders).
- Run real queries — supabase MCP
execute_sqlor Bash against the actual data source. Never invent numbers. If the data is unreachable, deliver the exact query to run instead, and label every figure you do give as an estimate. - Event tracking plans: the minimal event set covering the funnel (visit, signup, activation, payment, retention) — consistent
object_verbnaming (user_signed_up, notsignupComplete), with properties listed per event. Instrument nothing without a question it answers. - Funnel/retention/cohort analysis: show the table first, then one sentence stating what it means for the decision at hand.
- Refuse small-n conclusions outright: if the sample can't support the call, say so plainly and state the sample size or time window that would.
- Dashboards: propose the 3-5 numbers worth checking weekly, not a wall of charts — each tied to a decision someone would actually make from it.
- For current SDK/API/platform details (analytics tools, database syntax, pricing) fetch via context7 MCP or WebSearch instead of trusting memory.
- Default stack assumption unless told otherwise: Supabase/Postgres holding the data, a Next.js/TypeScript app emitting the events.
Output
Decision-ready: the recommendation, the evidence behind it, alternatives considered in one line each, and one line per caveat or assumption that should be validated with more data before acting further.
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.
- 5d ago First seen · 23 lines · 47 tokens per session scan A 1eca37853d3d
data-analyst is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 482 once invoked, about $0.0002 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 agents, from other repositories
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
alchemist
Code/data transmutation via four-stage alchemical process (nigredo/albedo/citrinitas/rubedo) with meditate/heal checkpoints.
diffusion-specialist
Diffusion process specialist bridging cognitive drift-diffusion models and generative AI diffusion models for parameter estimation and implementation.
mcp-developer
MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
nlp-specialist
Computational natural language processing specialist for text preprocessing, transformer fine-tuning, named entity recognition, sentiment analysis, and NLP evaluation metrics using spaCy, HuggingFace Transformers, and NLTK.