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 BanibrataChatterjee/AwesomeSalesforceSkills --skill data-cloud-calculated-insightsgit clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkillsWrote 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/banibratachatterjee/awesomesalesforceskills/data-cloud-calculated-insights)<a href="https://agentmods.dev/skills/banibratachatterjee/awesomesalesforceskills/data-cloud-calculated-insights"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/data-cloud-calculated-insights/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/banibratachatterjee/awesomesalesforceskills/data-cloud-calculated-insights"><img src="https://agentmods.dev/badge/skills/banibratachatterjee/awesomesalesforceskills/data-cloud-calculated-insights.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 | $0.00099 | $0.03829 |
| Opus 5 | $0.00049 | $0.01914 |
| Sonnet 5 | $0.00020 | $0.00766 |
| Haiku 4.5 | $0.00010 | $0.00383 |
Grade A, and why
data-cloud-calculated-insights 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 9d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Cloud Calculated Insights
This skill activates when a practitioner needs to design, author, or troubleshoot Calculated Insights in Data Cloud — batch SQL-based metrics that aggregate DMO data into persistent measures and dimensions attached to Unified Profiles. It also covers Streaming Insights for near-real-time signal use cases and the critical pre-build design decisions that cannot be changed after an insight is created.
Before Starting
Gather this context before working on anything in this domain:
- Finalize all dimension and measure API names before creation. Measure API names, measure data types, rollup behavior, and dimension names are immutable after a Calculated Insight is created. Only additive changes (adding new measures or dimensions) are allowed. Renaming or changing a type requires deleting the insight and recreating it, which loses all historical data.
- Confirm the use case requires Calculated Insights (batch) vs. Streaming Insights (real-time). Streaming Insights process only Mobile SDK and Marketing Cloud Personalization event sources in near-real time. They cannot join Unified Profiles, cannot produce lifetime aggregates, and cannot be used as segment filter conditions for batch segmentation. Mixing up these two types is the most common design error.
- Check org limits before adding insights. The org-wide maximum is 300 total insights (Calculated + Streaming combined). Streaming Insights are additionally capped at 20 per org. An org near its limit cannot create new insights regardless of SQL validity.
- Confirm available DMOs for the SQL. The Calculated Insight SQL must reference DMOs (not DLOs). Confirm that all required DMOs have been mapped and populated before authoring the SQL, or the insight will fail silently or return zero rows.
Core Concepts
SQL Authoring and the 131,021-Character Limit
Calculated Insights are authored using ANSI SQL in the Data Cloud UI's SQL editor. The SQL must use GROUP BY to define dimensions — every non-aggregated column in the SELECT must appear in the GROUP BY clause. Aggregation functions (COUNT, SUM, AVG, MIN, MAX) define measures. Subqueries, CTEs (WITH clauses), and joins across multiple DMOs are supported. The SQL has a hard character limit of 131,021 characters. This is rarely hit in practice but matters for complex multi-DMO joins.
What ships with it
6 files 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.
- 9d ago First seen · 219 lines · 99 tokens per session scan A d466d004dab4
data-cloud-calculated-insights is a skill published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 3,829 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
cml-admin
CML administration — user/group management, system info, licensing, resource monitoring. Use when creating CML users, checking license status, monitoring CML server resources, or auditing lab usage across teams.
tao-train-mask2former
Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Mask2Former model. Trigger phrases include "train Mask2Former", "universal…
tao-train-oneformer
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a TAO OneFormer model. Trigger phrases include "train OneFormer", "universal…
tao-train-segformer
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation tasks. Use when training, evaluating, exporting, quantizing, or running inference for a TAO SegFormer model. Trigger phrases include "train SegFormer", "semantic…
tao-train-visual-changenet
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pairs for PASS/NOPASS classification, or producing change-segmentation masks. Trigger phrases include…