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/exasol-labs/exasol-agent-skillsWrote 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/commands/exasol-labs/exasol-agent-skills/exasol)<a href="https://agentmods.dev/commands/exasol-labs/exasol-agent-skills/exasol"><img src="https://agentmods.dev/badge/commands/exasol-labs/exasol-agent-skills/exasol/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/commands/exasol-labs/exasol-agent-skills/exasol"><img src="https://agentmods.dev/badge/commands/exasol-labs/exasol-agent-skills/exasol.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 | $0.00014 | $0.00316 |
| Opus 5 | $0.00007 | $0.00158 |
| Sonnet 5 | $0.00003 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
exasol 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 7d 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
/exasol Command
Unified Claude Code entry point for Exasol work.
Usage
/exasol <Exasol task, SQL query, or question>
Behavior
- Activate the top-level exasol skill for the complete user request.
- Choose the narrowest specialized skill whose front-matter description matches the request, then apply the router's precedence rules, dependency order, user interaction rules, and safety rules. The top-level skill is the single source of truth; do not duplicate or reinterpret its rules here.
- Follow the selected specialized skill, including its prerequisites, validation, safety rules, and handoffs to related skills.
- Do not ask the user to select an internal skill. If the outcome is ambiguous, ask one concrete question about the desired result.
Examples
/exasol SELECT COUNT(*) FROM my_schema.my_table
/exasol upload sales_data.csv to analytics.sales
/exasol export the users table to CSV in S3
/exasol create a PostgreSQL JDBC virtual schema
/exasol build a custom virtual schema adapter for a new JDBC dialect
/exasol list BucketFS files under models/
/exasol which Exasol connector should I use for Databricks?
/exasol initialize the Text AI Extension for notebook-connector
/exasol write a Python UDF that normalizes product names
/exasol set up Exasol Personal on AWS
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.
- 7d ago Changed · +1 lines 25d421e582ae
- 11d ago First seen · 40 lines · 14 tokens per session scan A 87c20d2e2f18
exasol is a command published in the GitHub repository exasol-labs/exasol-agent-skills (10 stars, last pushed 7d ago), licensed MIT. It adds 14 tokens to every session and 316 once invoked, about $0.0001 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 commands, from other repositories
archetype-impact
Scan the current workspace for all references to a given archetype across templates (.oet / .t.json source, .opt compiled) and AQL files, producing an impact table useful before editing a widely-reused archetype.
cache
Hostile audit of caching correctness: assume every cache serves stale data after a write, shares a key across entities that must not share one, grows without bound, and stampedes on expiry — then prove where. A cache is a correctness liability until its key, its invalidation, its bound, and its expiry behavior are all…
migrations
Hostile single-shot audit of database schema and data migrations: assume every migration eats production until proven safe.
scaffold-mean
One-time project setup for a MEAN stack application. Initializes the project structure, installs dependencies, and creates base configuration files. Run this ONCE before the first /el-capitan invocation.
datamodel
Create or modify Prisma-based data models for Nimbalyst's DataModelLM visual editor.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.