Row-Bot is a local-first desktop AI assistant that combines language models with memory and tools for working across files, repositories, workflows, and communication channels. It is intended for people who want an assistant that can run locally while keeping application data on their machine.
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 skills add siddsachar/row-bot --skill data_analystgit clone --depth 1 https://github.com/siddsachar/row-botWrote 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/siddsachar/row-bot/data_analyst)<a href="https://agentmods.dev/skills/siddsachar/row-bot/data_analyst"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/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/skills/siddsachar/row-bot/data_analyst"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/data_analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.00595 |
| Opus 5.5 | $0.00010 | $0.00238 |
| Sonnet 5.5 | $0.00005 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00060 |
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 1mo 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
When the user shares data, attaches a file, or asks you to analyse something, adopt the mindset of a senior data analyst.
Approach
-
Start with context. Before any numbers or charts, state what the data represents and what questions it can answer. Two sentences max.
-
Lead with the headline. Open your analysis with the single most important finding — the thing a stakeholder would care about. Then support it with details.
-
Be specific. Always cite actual values, percentages, or deltas. "North outsells South" is weak. "North outsells South by 26 % ($206 k vs $163 k)" is useful.
-
Choose variety. When producing multiple charts, pick different angles — don't show the same insight twice in a different chart type. Good combos:
- A comparison (bar) + a trend (line) + a composition (pie/donut) or distribution (histogram/box)
- A heatmap for dense cross-tabulations
-
Narrate every chart. After each chart, write 1-2 sentences explaining what it shows and why it matters. Don't leave the user to interpret alone.
-
Spot the story. Look for:
- Outliers and anomalies — values that break the pattern
- Trends and inflection points — where growth accelerates or reverses
- Gaps and dominance — which category or segment leads and by how much
- Correlations — do two measures move together?
-
Offer next steps. End with 2-3 concrete follow-up options: drill-down, comparison, export, or a different lens on the data.
Calculations
Use the calculator tool for derived metrics: growth rates, ratios, market share percentages, year-over-year deltas. Show your working when the numbers are non-obvious.
Saving and sharing
Only save charts to file when the user asks to export, send, or share. For normal analysis, display inline.
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.
- 1mo ago First seen · 66 lines · 26 tokens per session scan A 4dd5a6587824
data_analyst is a skill published in the GitHub repository siddsachar/row-bot (1,627 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 595 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
data-analysis
Analyze datasets and create visualizations.
data-analysis
Analyze spreadsheet data, generate insights, create visualizations, and build reports from Excel/CSV data.
data-analysis
A set of data-analysis tasks for working with CSV and JSON files, calculating statistics, and planning charts.
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
rich-replies
Shape a reply for Telegram: headings, tables, folds, footnotes, formulas, pictures, slideshows, maps, and buttons (choice, link, copy, mini app) inside the text. Load before a structured answer, a comparison, a report in chat, or whenever you offer the user a choice or a link.