Borrowing it
Nothing to install: this file belongs to Leonides2/homemade-mcp-oracle-database-10g-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Leonides2/homemade-mcp-oracle-database-10g-claude/main/.claude/skills/oracle10g-query/SKILL.mdgit clone --depth 1 https://github.com/Leonides2/homemade-mcp-oracle-database-10g-claudeWrote 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/leonides2/homemade-mcp-oracle-database-10g-claude/oracle10g-query)<a href="https://agentmods.dev/skills/leonides2/homemade-mcp-oracle-database-10g-claude/oracle10g-query"><img src="https://agentmods.dev/badge/skills/leonides2/homemade-mcp-oracle-database-10g-claude/oracle10g-query/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/leonides2/homemade-mcp-oracle-database-10g-claude/oracle10g-query"><img src="https://agentmods.dev/badge/skills/leonides2/homemade-mcp-oracle-database-10g-claude/oracle10g-query.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 | $0.00091 | $0.01145 |
| Opus 5.5 | $0.00036 | $0.00458 |
| Sonnet 5.5 | $0.00018 | $0.00229 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
oracle10g-query 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 2mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consultas a Oracle 10g (solo lectura)
Esta skill envuelve el CLI de este repo (scripts/query.py) para consultar la
base de datos Oracle 10g del proyecto desde la terminal, sin necesidad de un
MCP client. Usa el mismo nucleo de conexion/seguridad que el servidor MCP
(src/mcp_server.py).
Regla no negociable: SOLO LECTURA
Esta base es un sistema legacy en produccion. La utilidad solo permite
sentencias SELECT (o WITH ... SELECT). Cualquier INSERT, UPDATE,
DELETE, MERGE, DDL (CREATE/ALTER/DROP/TRUNCATE), GRANT/REVOKE,
bloques PL/SQL o multiples sentencias separadas por ; son rechazados antes
de tocar la base (ver src/sql_guard.py). No intentes rodear esta
restriccion (por ejemplo con EXECUTE IMMEDIATE dentro de un SELECT, DB
links a otra sesion con permisos de escritura, etc.) — si el usuario
necesita escribir datos, dile que esta utilidad no lo soporta y que se
requiere un cambio explicito de alcance.
Requisito previo
Debe existir un archivo .env en la raiz del repo con las credenciales
(ver .env.example). Si no existe o falta una variable, el CLI lo reporta
claramente — no adivines valores de conexion.
Como ejecutar una consulta
Desde la raiz del repo, usando el interprete del entorno virtual del proyecto:
.venv\Scripts\python scripts\query.py "SELECT columnas FROM tabla WHERE ..."
Salida en JSON (mas facil de parsear para ti):
.venv\Scripts\python scripts\query.py "SELECT ..." --format json
Consulta desde un archivo .sql (util si la consulta es larga o multilinea):
.venv\Scripts\python scripts\query.py --file ruta\a\consulta.sql --format json
Antes de escribir un SELECT contra una tabla que no conoces
- Ver que tablas existen (opcionalmente filtrando por owner/schema):
.venv\Scripts\python scripts\query.py "SELECT owner, table_name FROM all_tables WHERE owner = 'ALGUN_SCHEMA' ORDER BY table_name" --format json - Ver las columnas de una tabla puntual antes de asumir su estructura:
.venv\Scripts\python scripts\query.py "SELECT column_name, data_type, data_length, nullable FROM all_tab_columns WHERE table_name = 'ALGUNA_TABLA' ORDER BY column_id" --format json
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.
- 2mo ago First seen · 101 lines · 91 tokens per session scan A eb62a25de690
oracle10g-query is a skill published in the GitHub repository Leonides2/homemade-mcp-oracle-database-10g-claude (0 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 1,145 once invoked, about $0.0004 per session on Opus 5.5. 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.
oracle10g-query compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oracle10g-queryLeonides2/homemade-mcp-oracle-database-10g-claude | Skill | 0 | 6d ago | MIT | A | 91 | Claude Code |
| create-prprisma/orm | Skill | 48k | today | Apache-2.0 | A | 47 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | yesterday | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 932 | yesterday | MIT | A | 79 | Claude Code, Codex |
| dsqlawslabs/agent-plugins | Skill | 947 | 2d ago | Apache-2.0 | A | 247 | Claude Code |