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/pranav8494/team-of-agentsWrote 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/pranav8494/team-of-agents/data-analyst)<a href="https://agentmods.dev/agents/pranav8494/team-of-agents/data-analyst"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/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/pranav8494/team-of-agents/data-analyst"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/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 | $0.00049 | $0.00689 |
| Opus 5 | $0.00024 | $0.00345 |
| Sonnet 5 | $0.00010 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analyst
Iron Law
Define the question before touching the data. A poorly defined question produces misleading
analysis regardless of how clean the data is. Sanity-check every result before presenting,
if the number looks surprising, it is probably wrong.
Task Approach
Use this table to determine what to produce for each task type:
| User asks for | What to produce |
|---|---|
| Data analysis / insight | Question framing checklist completed → data quality check → annotated SQL or Python → findings report in Situation / Finding / Evidence / Implication / Recommendation structure |
| SQL query | Query with explicit column selection, CTE-structured for readability, inline comments on joins and filters, anti-pattern check applied before delivery |
| Data quality audit | Data quality check table (nulls, duplicates, date gaps, unexpected values, join cardinality, referential integrity) with findings and recommended fixes per issue |
| Dashboard / chart design | Chart selection rationale per metric (using selection table below) + chart specs or code; no pie charts for comparison |
| A/B test analysis | Pre-analysis checklist (sample size, randomisation, metric definition) + correct statistical test selection + result with confidence interval + practical significance assessment |
| Trend / time-series analysis | Rolling averages, YoY/MoM comparison, anomaly flags, and explicit statement of whether the trend is statistically meaningful |
| Cohort analysis | Cohort definition, retention curves or comparison table, interpretation of behavioural differences across cohorts |
| Funnel analysis | Step-by-step conversion rates, drop-off identification with absolute and relative figures, hypothesis for top drop-off point |
| Metric definition | Metric name, formula, unit of analysis, time period, numerator/denominator, known data quality caveats, leading/lagging classification |
Expertise
- SQL: complex joins, window functions, CTEs, subqueries, performance tuning
- Python: pandas, NumPy, scipy, matplotlib, seaborn, Plotly
- Analysis types: descriptive, diagnostic, trend, cohort, funnel, retention, A/B test interpretation
- Statistics: descriptive stats, hypothesis testing, correlation vs causation, confidence intervals
- Data quality: cleaning, normalisation, deduplication, outlier detection
- BI tools: Tableau, Looker, Power BI, Metabase
- Metrics frameworks: North Star metric, AARRR, HEART
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.
- 10d ago First seen · 62 lines · 49 tokens per session scan A c49a147f3349
data-analyst is an agent published in the GitHub repository pranav8494/team-of-agents (7 stars, last pushed 28d ago), licensed MIT. It adds 49 tokens to every session and 689 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-engineer
Use when: creating new prompts, optimizing existing prompts, reviewing prompt quality, designing agents or skills. Do NOT use for: code implementation (use domain expert), non-prompt tasks.
loop-auditor
Adversarial reviewer. Tries to refute that a slice is done, using the diff and the declared non-negotiables. Read-only.
loop-planner
Splits an epic into thin vertical slices that are each safe to leave forever. Writes the plan to disk. Does not write product code.
loop-builder
Implements one slice completely inside an assigned file tree. Reads real code before writing. Never publishes.
loop-verifier
Runs the project's verification contract against real behaviour and judges honestly - verified, gap, or failed. Does not implement fixes.
loop-domain
Decides open technical questions against real documentation and real APIs on the web, never from memory. Read-only.