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 Omar-Obando/qwen-orchestrator --skill sql-best-practicesgit clone --depth 1 https://github.com/Omar-Obando/qwen-orchestratorWrote 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/omar-obando/qwen-orchestrator/sql-best-practices)<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/sql-best-practices"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/sql-best-practices/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/omar-obando/qwen-orchestrator/sql-best-practices"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/sql-best-practices.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 | $0.00041 | $0.01466 |
| Opus 5 | $0.00020 | $0.00733 |
| Sonnet 5 | $0.00008 | $0.00293 |
| Haiku 4.5 | $0.00004 | $0.00147 |
Grade A, and why
sql-best-practices 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 9d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Best Practices — Every Query a Masterpiece
This skill enforces SQL quality standards: proper indentation, N+1 prevention, parameterized queries, index-friendly patterns, and security.
SQL Indentation Standard
EVERY SQL query MUST be properly indented:
-- ✅ CORRECT: Properly formatted
SELECT
u.id,
u.name,
u.email,
u.created_at,
r.name AS role_name,
d.name AS department_name
FROM
users u
INNER JOIN roles r
ON r.id = u.role_id
LEFT JOIN departments d
ON d.id = u.department_id
WHERE
u.deleted_at IS NULL
AND u.status = 'active'
AND u.created_at >= '2024-01-01'
ORDER BY
u.created_at DESC
LIMIT 20
OFFSET 0;
-- ❌ WRONG: No formatting
select id,name,email from users where deleted_at is null and status='active' order by created_at desc limit 20;
Formatting Rules
- Keywords: UPPERCASE (SELECT, FROM, WHERE, JOIN, etc.)
- Indentation: Each clause on its own line, indented
- Columns: One per line in SELECT
- JOIN conditions: Indented under the JOIN
- WHERE conditions: Aligned AND/OR
- Commas: Leading or trailing — pick one, be consistent
N+1 Prevention Patterns
Detection Pattern
If you see a LOOP containing a QUERY, it's likely N+1.
Count queries: 1 (initial) + N (loop) = N+1 problem.
Solution: Eager Loading
-- ❌ N+1: One query per order for items
SELECT * FROM orders WHERE user_id = 123;
-- Then for EACH order:
SELECT * FROM order_items WHERE order_id = ?;
-- ✅ Single query with JOIN
SELECT
o.id AS order_id,
o.total AS order_total,
o.status AS order_status,
oi.id AS item_id,
oi.product_name,
oi.quantity,
oi.unit_price
FROM
orders o
INNER JOIN order_items oi
ON oi.order_id = o.id
WHERE
o.user_id = 123
AND o.deleted_at IS NULL
ORDER BY
o.created_at DESC,
oi.id ASC;
Solution: Batch with IN
-- ❌ N+1: Loop over IDs
SELECT * FROM products WHERE id = 1;
SELECT * FROM products WHERE id = 2;
SELECT * FROM products WHERE id = 3;
-- ✅ Batch: Single query
SELECT
id,
name,
sku,
price,
stock_quantity
FROM
products
WHERE
id IN (1, 2, 3)
AND deleted_at IS NULL;
What ships with it
1 file 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.
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.
- 9d ago First seen · 248 lines · 41 tokens per session scan A 4ffe2f0a6451
sql-best-practices is a skill published in the GitHub repository Omar-Obando/qwen-orchestrator (49 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,466 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 2026-09-03.
Other skills, from other repositories
warehouse-sql
Review and run read-only natural-language SQL against a customer data warehouse with cached schema introspection and explicit write grants.
architect-agent
A high-level system design expert. Use when: (1) planning new system architectures, (2) designing database schemas, (3) evaluating tech stacks, (4) creating technical design documents (TDD). This agent uses the sqlite-mcp to maintain a persistent architectural log for the project.
data-quality-fixer
A data-quality repair process in which one role proposes database fixes and another independently checks them on a copy before changes are saved.
buckets
Spaces are stateless. All data is wiped on restart / rebuild. For state that must survive (user uploads, generations, dynamic feeds, logs, growing databases): mount an HF Bucket — S3-like object storage living at hf://buckets/ / .
Arquitetura de Sistemas de Dados
Aborda princípios e práticas para projetar sistemas de dados escaláveis e eficientes.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.