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 DavidROliverBA/ArchitectKB --skill datasourcegit clone --depth 1 https://github.com/DavidROliverBA/ArchitectKBWrote 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/davidroliverba/architectkb/datasource)<a href="https://agentmods.dev/skills/davidroliverba/architectkb/datasource"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/datasource/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/davidroliverba/architectkb/datasource"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/datasource.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 | $0.00000 | $0.01209 |
| Opus 5.5 | $0.00000 | $0.00484 |
| Sonnet 5.5 | $0.00000 | $0.00242 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
datasource 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/datasource
Create a DataSource note documenting a specific database, table, API endpoint, dataset, or data entity with schema, quality metrics, and access information.
Usage
/datasource <name>
/datasource "SAP Invoices"
/datasource "DataPlatform Revenue Fact Table"
/datasource "Snowflake Customers"
Instructions
Phase 1: Parse Input & Link to System
- Extract data source name
- Ask which system owns this data:
Which system owns this data source? Search: [user searches for System] Or create new System? (Y/n) - Confirm link: "Link to [[System - {{system}}]]? (Y/n)"
Phase 2: Essential Information
Creating DataSource: {{name}} (owned by {{system}})
1️⃣ Data Type:
- database-table (relational table)
- database-view (virtual table)
- api-endpoint (REST/GraphQL data)
- kafka-topic (event stream)
- data-warehouse-table (Snowflake/BigQuery)
- data-lake (file-based storage)
- cache (Redis/Memcached)
Default: database-table
User input: [selection]
2️⃣ Record Count (approximate):
Default: null
User input: [number, e.g., 5000000]
3️⃣ Data Volume per Day:
Default: null
User input: [e.g., "2.5GB", "500K records"]
4️⃣ Refresh Frequency:
- real-time
- hourly
- daily
- weekly
- on-demand
Default: daily
User input: [selection]
5️⃣ Classification:
- public
- internal
- confidential
- secret
Default: internal
User input: [selection]
Phase 3: Data Quality (Optional)
Ask: "Add data quality metrics? (Y/n)"
If YES:
- Completeness (%): 98.5
- Uniqueness (%): 99.9
- Accuracy: high | medium | low
- Timeliness: how fresh (< 5 minutes, < 1 hour, etc.)
Phase 4: Schema & Key Fields
Key Fields (comma-separated):
invoice_id, vendor_id, amount
Then ask:
Schema details needed? (Y/n)
- Parent entities (sources of this data)
- Child entities (what feeds from this)
- Related tables
Phase 5: Access & Consumers
How is this data accessed?
- REST API
- GraphQL
- Direct database query
- Kafka topic
- Batch export / S3
- Other
Default: [based on data type]
Which systems consume this data?
Search: [[System - DataPlatform]]
Add: [[System - Analytics]]
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 · 227 lines · 0 tokens per session scan A 6f32b6ac7cd8
datasource is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (53 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,209 tokens. 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
lark-base
A guide for managing Lark Base, Feishu's spreadsheet-like database and workspace tool. It covers tables, fields, records, views, formulas, forms, dashboards, applications, workflows, and permissions.
smart-data-collection
A workflow for extracting structured information from images and documents such as PDFs, Word files, and spreadsheets, then storing it in a database.
entity-model
Creates entity model documents with Mermaid.js ER diagrams and attribute tables defining entities, relationships, data types, and validation rules. Use when the user asks to "create an entity model", "design a data model", "draw an ERD", "define database schema", "model entities", or mentions entity-relationship…
paper-interpretation
A Chinese-language workflow for explaining an academic paper from a PDF file or URL in accessible Markdown, with illustrations and critical assessment.
siyuan-mcp-import-migration
MCP staged playbook for Markdown and external database migration with explicit targets, mappings, bounded writes, and layered readback.
data-export-and-restore
Enforces user-facing data portability in an offline-first app — backup/restore (exact, machine round-trippable) kept strictly separate from export/report (human, lossy, never a restore source); a versioned envelope carrying formatVersion, schemaVersion, appVersion, exportedAtUtc and a payload checksum so a restore…