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 sAjAd-2006/bizinsight-agent --skill insight-generationgit clone --depth 1 https://github.com/sAjAd-2006/bizinsight-agentWrote 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/sajad-2006/bizinsight-agent/insight-generation)<a href="https://agentmods.dev/skills/sajad-2006/bizinsight-agent/insight-generation"><img src="https://agentmods.dev/badge/skills/sajad-2006/bizinsight-agent/insight-generation/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/sajad-2006/bizinsight-agent/insight-generation"><img src="https://agentmods.dev/badge/skills/sajad-2006/bizinsight-agent/insight-generation.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 | $0.00050 | $0.00513 |
| Opus 5 | $0.00025 | $0.00257 |
| Sonnet 5 | $0.00010 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
insight-generation 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.
What it actually says
Insight Generation Skill
Insight Frameworks
Apply the following frameworks to extract insights from analysis results:
1. Pareto Insight (80/20 Analysis)
- Identify the vital few factors driving the majority of outcomes
- Example: "20% of products generate 80% of revenue"
- Quantify the concentration ratio
2. Growth Pattern Insight
- Identify segments with highest/lowest growth rates
- Calculate compound growth rates where applicable
- Distinguish between one-time spikes and sustained trends
- Format: "[Segment] grew [X]% over [period], driven by [cause]"
3. Gap Analysis Insight
- Compare actual performance against benchmarks or targets
- Identify the largest performance gaps
- Quantify the opportunity cost of gaps
- Format: "[Metric] is [X]% below [benchmark], representing [value] in missed opportunity"
4. Anomaly Narration
- Transform statistical anomalies into business narratives
- Propose plausible business explanations for anomalies
- Assess whether anomalies are positive or negative signals
- Format: "Unusual [event] in [period] — [possible cause], [impact assessment]"
5. Correlation Insight
- Translate statistical correlations into business relationships
- Distinguish correlation from causation
- Identify leverage points for intervention
- Format: "[Variable A] and [Variable B] show [strength] correlation ([r=X]), suggesting [business implication]"
Impact Prioritization
Rate each insight on three dimensions:
| Dimension | High | Medium | Low |
|---|---|---|---|
| Financial Impact | > 20% revenue/cost change | 5-20% change | < 5% change |
| Actionability | Clear next steps exist | Some investigation needed | Informational only |
| Urgency | Time-sensitive window | Important but not urgent | Long-term consideration |
Output Format
For each insight provide:
- Finding: One-sentence description
- Evidence: Supporting data points
- Impact: High/Medium/Low with rationale
- Recommendation: Specific action to take
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 61 lines · 50 tokens per session scan A dba221269ca8
insight-generation is a skill published in the GitHub repository sAjAd-2006/bizinsight-agent (2 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 513 once invoked, about $0.0003 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 skills, from other repositories
datalens-dataset-wizard
Use when creating, updating, validating, or previewing DataLens datasets and native Wizard charts.
datalens-editor
Use when authoring or diagnosing DataLens JavaScript Editor table, Gravity, Advanced, Markdown, or selector charts.
datalens-maintenance
Use when exporting DataLens backups, inventorying administrative capabilities, or previewing and applying dependency-safe cleanup.
datalens-dashboard
Use when composing or updating DataLens dashboards, widgets, tabs, selectors, parameters, relations, styles, or layout.
datalens-inspect
Use when inspecting DataLens authentication, workbooks, dashboards, charts, datasets, connections, relations, or current errors without mutation.
wren-dlt-connector
Connect SaaS data (HubSpot, Stripe, Salesforce, GitHub, Slack, etc.) to Wren Engine for SQL analysis. Guides the user through the full flow: install dlt, pick a SaaS source, set up credentials, run the data pipeline into DuckDB, then auto-generate a Wren semantic project from the loaded data. Use this skill whenever…