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 inbharatai/claude-skills --skill sql-analystgit clone --depth 1 https://github.com/inbharatai/claude-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/inbharatai/claude-skills/sql-analyst)<a href="https://agentmods.dev/skills/inbharatai/claude-skills/sql-analyst"><img src="https://agentmods.dev/badge/skills/inbharatai/claude-skills/sql-analyst.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00404 |
| Opus 5 | $0.00013 | $0.00202 |
| Sonnet 5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
sql-analyst 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 4d 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.
This is a copy
78% identical to generating-quality-gate-workflows — 157 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
SQL Analyst
Overview
Perform SQL-based data analysis — exploratory queries, aggregations, funnels, cohorts, and insight narratives.
When to Use This Skill
Use SQL Analyst when you need to:
- Work with sql analyst tasks in your project or workflow
- Automate sql analyst operations at scale
- Generate production-quality sql analyst output quickly
Instructions
When this skill is active, Claude will:
- Understand the full context of your sql analyst request
- Apply best practices and conventions for Data & Analytics
- Produce clean, well-structured, production-ready output
- Explain key decisions and offer alternatives where relevant
Examples
Example 1 — Basic Usage
User: Help me get started with sql analyst.
Claude: I'll walk you through the essential steps for sql analyst in your context...
Example 2 — Advanced Usage
User: I need a production-ready sql analyst setup with full error handling.
Claude: Here's a complete, production-hardened sql analyst implementation...
Guidelines
- Always validate inputs before processing
- Follow the conventions of the target platform or language
- Prefer explicit over implicit — clarity beats cleverness
- Include comments for non-obvious logic
- Suggest tests or validation steps where appropriate
Dependencies
Required: postgresql, bigquery, snowflake
Platforms
Available on: claude.ai, claude-code, api
Part of the claude-skills collection — 183+ skills for Claude.
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.
- 4d ago First seen · 68 lines · 25 tokens per session scan A c9280c14e4e0
sql-analyst is a skill published in the GitHub repository inbharatai/claude-skills (33 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 404 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 78% identical to generating-quality-gate-workflows, differing in 157 lines, and is treated as a copy.
Other skills, from other repositories
mongo-migration
MongoDB schema migration safety reviewer and migration script generator. ALWAYS use when writing, reviewing, or planning MongoDB schema changes — field additions/removals, index builds, schema validator changes, document type migrations, shard key modifications, or any bulk update touching production collections.…
mysql-migration
MySQL schema migration safety reviewer and DDL generator. ALWAYS use when writing, reviewing, or planning MySQL schema changes — ALTER TABLE, CREATE/DROP INDEX, column type changes, charset conversions, data backfills, or any DDL touching production tables. Covers online DDL algorithm selection (INSTANT/INPLACE/COPY)…
oracle-migration
Oracle Database schema migration safety reviewer and DDL generator. ALWAYS use when writing, reviewing, or planning Oracle schema changes — ALTER TABLE, CREATE/DROP INDEX, column type changes, constraint additions, partition DDL, or any DDL touching production tables. Covers DDL auto-commit implications…
pg-migration
PostgreSQL schema migration safety reviewer and DDL generator. ALWAYS use when writing, reviewing, or planning PostgreSQL schema changes — ALTER TABLE, CREATE/DROP INDEX, column type changes, constraint additions, RLS policy changes, or any DDL touching production tables. Covers lock-level analysis, CREATE INDEX…
redis-cache-strategy
Redis caching strategy designer and reviewer. ALWAYS use when designing, reviewing, or troubleshooting Redis caching layers — cache pattern selection (cache-aside, write-through, write-behind), TTL strategy, cache stampede/penetration/avalanche prevention, hot key handling, cache-DB consistency, distributed locking…
DataWarehouseArchitect
Complete modern data stack intelligence — data warehouse design (Snowflake/BigQuery/Redshift), dbt transformation layer, ingestion pipelines, data catalog, data quality, and building a data platform that the whole company can use.