Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace/plugin install pwdev-postgresWrote 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/pwdev-solucoes/pwdev-claude-marketplace/postgres)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/postgres"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/postgres.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 | $0.00115 | $0.01229 |
| Opus 5 | $0.00057 | $0.00615 |
| Sonnet 5 | $0.00023 | $0.00246 |
| Haiku 4.5 | $0.00012 | $0.00123 |
Grade A, and why
postgres 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postgres
Você opera o PostgreSQL do usuário via servidor MCP postgres.
Pré-requisito e degradação
Path A — MCP postgres conectado: use as tools diretamente.
Path B — tools falhando ou MCP ausente: não simule resultado de banco.
Sem DATABASE_URL este servidor nem sobe (exit 1 no boot — não há modo
placeholder): /mcp mostrando o servidor com erro significa config ausente
na sessão. Diagnostique com ${CLAUDE_PLUGIN_ROOT}/scripts/check-setup.sh e
aponte /pwdev-postgres:init. Env var nova só vale após reiniciar a sessão.
Não escreva SQL por fora (psql direto) para contornar o MCP — psql é só
diagnóstico do check-setup.
Mapa de intenção → tool
| Intenção | Tool |
|---|---|
| Consultar dados / EXPLAIN | run_select — sempre com LIMIT explícito |
| Ver estrutura de tabela | describe_table (colunas, PK, FKs, constraints, índices) |
| Listar tabelas | list_tables (include_views: true p/ views) |
| Listar schemas | list_schemas |
| Listar índices | list_indexes |
| Constraints de uma tabela | list_constraints |
| Inserir uma linha | insert_row |
| Atualizar linhas | update_rows — set e where obrigatórios |
| Deletar linhas | delete_rows — where obrigatório |
| Criar tabela | create_table |
| Alterar tabela | alter_table — UMA ação por chamada |
| Derrubar tabela | drop_table |
| Criar índice | create_index (só btree) |
| Derrubar índice | drop_index |
Parâmetros exatos e pegadinhas: ${CLAUDE_PLUGIN_ROOT}/references/mcp-tools.md.
Sem prompts nem resources MCP — só as 14 tools.
Regras de segurança (inegociáveis)
- Mutação sempre em duas fases. Toda tool DML/DDL tem dry-run
obrigatório: chame primeiro com
confirm: false, mostre ao usuário o preview (sql,estimatedRows,warnings) e só repita comconfirm: trueapós confirmação explícita dele no chat. Nunca emende as duas chamadas sem a confirmação no meio. run_selectsempre comLIMIT— o servidor não impõe limite de linhas; uma query sem LIMIT pode despejar a tabela inteira no contexto.- Nunca contorne as travas do servidor:
update_rows/delete_rowssemwheresão rejeitados por design (anti mutação em massa) — não simule o efeito com umwheretautológico ({"1":"1"}etc.). cascadeé confirmação reforçada: emdrop_table/drop_columncomcascade, liste os dependentes do preview e confirme nominalmente.- Leia
.claude/pwdev-postgres-context.mdantes de qualquer mutação — ambiente (produção?), tabelas críticas e se DDL é permitido. Em produção, redobre: proponha, não execute sem confirmação explícita. alter_tablereal:add_column|drop_column|rename_column|set_default|set_nullable— uma ação por chamada (o README do servidor tem drift; estes são os nomes do código).- Valores sempre via
params/records — nunca interpole valor do usuário em SQL derun_select.
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 · 97 lines · 115 tokens per session scan A a2f321fcb835
postgres is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 115 tokens to every session and 1,229 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 2026-09-03.
Other skills, from other repositories
alloydb-basics
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
db-repair
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a GBRAINDBACCESS marker (or an operator reports the brain database is down), run the hardcoded gbrain db-repair ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command …
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.