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/mcp-server --skill exasol-table-designgit clone --depth 1 https://github.com/exasol/mcp-serverWrote 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/mcp-server/exasol-table-design)<a href="https://agentmods.dev/skills/exasol/mcp-server/exasol-table-design"><img src="https://agentmods.dev/badge/skills/exasol/mcp-server/exasol-table-design.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.02996 |
| Opus 5 | $0.00018 | $0.01498 |
| Sonnet 5 | $0.00007 | $0.00599 |
| Haiku 4.5 | $0.00004 | $0.00300 |
Grade A, and why
exasol-table-design 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 8d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exasol Table Design
CREATE TABLE Syntax
CREATE [OR REPLACE] TABLE [IF NOT EXISTS] schema.table_name (
column_name data_type [DEFAULT value] [IDENTITY [start [INCREMENT BY step]]]
[NOT NULL] [PRIMARY KEY] [REFERENCES ref_table (ref_col)],
...,
[PRIMARY KEY (col1, col2, ...)],
[FOREIGN KEY (col) REFERENCES ref_table (ref_col)],
[LIKE other_table [INCLUDING DEFAULTS] [INCLUDING IDENTITY] [INCLUDING COMMENTS]],
[DISTRIBUTE BY col1 [, col2, ...]],
[PARTITION BY col]
);
Key options:
| Clause | Effect |
|---|---|
OR REPLACE |
Silently overwrites an existing table |
IF NOT EXISTS |
No-op if the table already exists |
LIKE t |
Copies column definitions (not constraints) from t; add INCLUDING DEFAULTS / INCLUDING IDENTITY / INCLUDING COMMENTS to copy those properties |
DISTRIBUTE BY |
Controls how rows are spread across cluster nodes |
PARTITION BY |
Controls physical data layout within each node |
CREATE TABLE AS
-- Create and populate from a query
CREATE TABLE new_table AS SELECT * FROM source_table;
-- Create schema only (no data)
CREATE TABLE new_table AS SELECT * FROM source_table WITH NO DATA;
Data Types
Choose the smallest type that fits the data — oversized declarations waste memory and slow comparisons.
| Type | Recommendation |
|---|---|
DECIMAL(p, s) |
Preferred exact numeric; use instead of DOUBLE when precision matters |
DOUBLE / FLOAT |
64-bit floating point; only when approximate arithmetic is acceptable |
VARCHAR(n) |
Variable-length string; avoid declaring much larger than needed (e.g. VARCHAR(2000000) when 100 suffices) |
CHAR(n) |
Fixed-length; prefer over VARCHAR when all values have the same length (e.g. ISO country codes) |
DATE |
Calendar date only; use instead of TIMESTAMP when time-of-day is irrelevant |
TIMESTAMP(p) |
Include time; default precision is 3 (milliseconds) |
BOOLEAN |
For true/false flags |
HASHTYPE(n BYTE) |
Fixed-length binary hashes (UUIDs, MD5 digests, etc.) |
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.
- 8d ago First seen · 347 lines · 36 tokens per session scan A 64b992eb8614
exasol-table-design is a skill published in the GitHub repository exasol/mcp-server (18 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 2,996 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
frontmcp-production-readiness
Pre-production audit, hardening, and go-live checklists for FrontMCP servers. Use before shipping to verify security hardening, performance, reliability, and observability, and for target-specific production checklists: Node server (Docker, graceful shutdown, Redis session scaling), Vercel and edge (cold-start…
pg-bloat-analysis
Detects and remediates table and index bloat in PostgreSQL using pgstattuple analysis. Identifies fragmentation, dead tuples, and wasted space with prioritized maintenance actions including VACUUM, REINDEX, and pgrepack recommendations.
pg-health-check
Performs comprehensive PostgreSQL database health assessments covering connections, cache performance, locks, replication, wait events, active queries, and configuration review. Produces a scored health report with prioritized recommendations.
pg-index-optimization
Performs comprehensive PostgreSQL index optimization including unused index cleanup, duplicate detection, missing index recommendations, and hypothetical index testing with HypoPG. Provides actionable CREATE/DROP INDEX statements with estimated impact.
pg-lock-diagnosis
Diagnoses PostgreSQL lock contention including blocking lock chains, deadlock patterns, idle-in-transaction problems, and wait event analysis. Guides the agent through identifying blockers, understanding lock types, and recommending transaction and configuration changes.
pg-performance-baseline
Generates a comprehensive PostgreSQL performance baseline report capturing health metrics, query workload patterns, table statistics, configuration settings, index utilization, and I/O patterns. Designed for before/after comparison when making changes.