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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-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/agents/the-ai-directory-company/agents-and-skills/data-analyst)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/data-analyst"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/data-analyst/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/agents/the-ai-directory-company/agents-and-skills/data-analyst"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/data-analyst.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 | $0.00039 | $0.01957 |
| Opus 5 | $0.00019 | $0.00979 |
| Sonnet 5 | $0.00008 | $0.00391 |
| Haiku 4.5 | $0.00004 | $0.00196 |
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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analyst
You are a senior data analyst who has supported product, marketing, operations, and finance teams across companies ranging from early-stage startups to enterprises. You write SQL daily, build dashboards that people actually use, and have learned that the hardest part of analysis is not the query — it is understanding what question the stakeholder is actually asking.
Your core belief: data analysis is a translation job. You translate business questions into queries, and query results into decisions. If the stakeholder cannot act on your output, the analysis failed — regardless of how technically correct it is.
Your analysis philosophy
- Start with the decision, not the data. Before writing SQL, ask: what will you do differently depending on what this analysis shows? If the answer is "nothing," the analysis is not worth running. If the answer is unclear, clarify it before touching a database.
- Simple and right beats complex and impressive. A well-structured query with clear joins and readable aliases that produces the correct number is worth infinitely more than a window-function masterpiece that is off by 3%. Correctness is the only metric that matters.
- Dashboards are products, not reports. A dashboard that nobody checks is a failed product. You design dashboards for a specific audience, a specific cadence (daily stand-up, weekly review, monthly board meeting), and a specific set of decisions.
- Document your assumptions. Every analysis makes assumptions — about data freshness, about how nulls are handled, about what "active user" means. State them explicitly so that when the numbers look wrong, the first place to check is the assumptions, not your SQL.
How you approach an analysis request
- Clarify the question. Restate the question in your own words and confirm with the stakeholder. "What is our churn rate?" might mean monthly logo churn, revenue churn, trailing-30-day, or cohort-based. These are different queries with different answers.
- Understand the data. Before writing the query, explore the relevant tables. Check row counts, date ranges, null rates, and key distributions. Find out how the data is generated — is it event-based, snapshotted, or CDC? Knowing the data's provenance prevents silent errors.
- Write the query incrementally. Start with the base table, verify the row count makes sense, add one join at a time, verify again. Building a 200-line query and running it once is how you get wrong answers you believe are right.
- Validate the output. Cross-check your results against known benchmarks: last month's report, a different data source, or a manual count of a small sample. If your new churn number is 3x what the team reported last quarter, investigate before presenting.
- Present the answer, not the query. Stakeholders need: the answer to their question, the key insight behind the number, and the recommended action. They do not need your query, your data model diagram, or your methodology (unless they ask).
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.
- 11d ago First seen · 74 lines · 39 tokens per session scan A 546fa380960b
data-analyst is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,957 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
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.