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 exasol-labs/exasol-agent-skills --skill exasol-databasegit 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/skills/exasol-labs/exasol-agent-skills/exasol-database)<a href="https://agentmods.dev/skills/exasol-labs/exasol-agent-skills/exasol-database"><img src="https://agentmods.dev/badge/skills/exasol-labs/exasol-agent-skills/exasol-database/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/exasol-labs/exasol-agent-skills/exasol-database"><img src="https://agentmods.dev/badge/skills/exasol-labs/exasol-agent-skills/exasol-database.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 | $0.00110 | $0.01426 |
| Opus 5 | $0.00055 | $0.00713 |
| Sonnet 5 | $0.00022 | $0.00285 |
| Haiku 4.5 | $0.00011 | $0.00143 |
Grade A, and why
exasol-database 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exasol Database Skill
Trigger when the user asks for Exasol database interaction, exapump, Exasol SQL, EXA_ system views, schemas, tables, or query execution outside exasol-import and exasol-export.
Step 0: Establish Connection
Ensure a working exapump profile before proceeding:
- If the user names a profile, test it with
exapump sql --profile <name> "SELECT 1"; always place--profileafter the subcommand. Otherwise test the default profile withexapump sql "SELECT 1". - On success, proceed — and keep the same
--profile <name>after the subcommand on every laterexapumpcommand. - On failure, run
exapump profile listto see which profiles exist. - If profiles exist, present them and ask which to use, then inspect that one with
exapump profile show <name>— it masks credentials — to confirm the required fields are set. Never read,cat, or print~/.exapump/config.toml; it stores credentials in clear text. If a credential value does appear in any command output, do not repeat it in the conversation. - If no usable profile exists, have the user create one locally with
exapump profile add <name>(omit--passwordand exapump prompts on a hidden line) orexapump profile init, then retry step 1. Never ask the user to paste a password into the conversation, and never pass one as a command-line argument.
Routing Algorithm
After the connection is established, determine the task type and load only the references needed:
- SQL execution (queries, DDL, DML, schema inspection):
- Load:
references/exapump-reference.md(CLI usage) - Load:
references/exasol-sql.md(core SQL behavior) - Load:
references/exasol-grammar.mdfor the exact statement syntax (SELECT/DQL, DDL, DML, DCL, session & admin) — the EBNF the docs.exasol.com syntax diagrams are generated from. Consult it before inventing syntax or when unsure a clause exists. Read only the section you need — it is large. - Load:
references/exasol-grammar-functions.mdfor built-in function, operator, predicate, literal, and data-type syntax (e.g. the exact argument order of a function). Same EBNF source, split out so statement lookups don't pull in the full function catalog. - Load:
references/exasol-reserved-keywords.mdand ingest the full list before designing queries — every reserved word (pinned to Exasol 2026.1.0) must be double-quoted when used as an identifier. On a keyword-related syntax error, re-query the running DB as described in Before writing any SQL in case the file has drifted from the DB version.
- Load:
What ships with it
8 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.
- references/analytics-qualify.md 3.5 KB
- references/exapump-reference.md 1.8 KB
- references/exasol-grammar-functions.md 20 KB
- references/exasol-grammar.md 24 KB
- references/exasol-reserved-keywords.md 6.3 KB
- references/exasol-sql.md 8.7 KB
- references/query-profiling.md 2.0 KB
- references/table-design.md 2.6 KB
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 · -2 lines · +61 tokens per session 3d24a0df19c1
- 11d ago First seen · 67 lines · 49 tokens per session scan A 7de2fb2bb64b
exasol-database is a skill published in the GitHub repository exasol-labs/exasol-agent-skills (10 stars, last pushed 7d ago), licensed MIT. It adds 110 tokens to every session and 1,426 once invoked, about $0.0006 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
dynamodb
AWS DynamoDB NoSQL database for scalable data storage. Use when designing table schemas, writing queries, configuring indexes, managing capacity, implementing single-table design, or troubleshooting performance issues.
rds
AWS RDS relational database service for managed databases. Use when provisioning databases, configuring backups, managing replicas, troubleshooting connectivity, or optimizing performance.
using-datavault4dbt
Builds Data Vault 2 models in dbt with the datavault4dbt package — staging, hubs, links, satellites, and business-vault entities — using the YAML-metadata macro pattern with correct hashkeys, hashdiffs, naming, and materializations. Use when creating or editing datavault4dbt models, setting up a raw vault, choosing…
configuring-datavault4dbt
Installs and configures the datavault4dbt package in a dbt project — packages.yml, copying the global vars into dbtproject.yml, hash and naming settings, and per-adapter setup. Use when setting up datavault4dbt, installing the package, changing hash/naming global variables, or adapting configuration for a specific…
rehashing-datavault4dbt-entities
Recalculates hashkeys and hashdiffs across an existing raw vault with datavault4dbt's rehashing macros after a change to the hash algorithm, datatype, trimming, or case sensitivity — including the v1→v2.0.0 upgrade. Use when changing hash global variables, migrating hash logic, or upgrading datavault4dbt without…
testing-a-datavault4dbt-project
Adds Data Vault 2 technical tests to a datavault4dbt project — hashkey uniqueness and not-null, link-to-hub referential integrity, and satellite key+load-date uniqueness — as dbt soft-constraint tests in YAML. Use when adding or reviewing tests for hubs, links, or satellites, or validating raw vault integrity.