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 agentmods add instructions/secretx33/postgres-ssh-mcp/claude-mdgit clone --depth 1 https://github.com/SecretX33/postgres-ssh-mcpWrote 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/instructions/secretx33/postgres-ssh-mcp/claude-md)<a href="https://agentmods.dev/instructions/secretx33/postgres-ssh-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/secretx33/postgres-ssh-mcp/claude-md.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 | $0.00752 | $0.00752 |
| Opus 5 | $0.00376 | $0.00376 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
postgres-ssh-mcp CLAUDE.md 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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
pnpm install # Install dependencies
pnpm build # Bundle with tsdown (→ dist/)
pnpm test # Run all tests (vitest)
pnpm test -- tests/sql-validator.test.ts # Run a single test file
pnpm typecheck # Type-check without emitting
pnpm format # Check formatting (prettier)
pnpm format:write # Auto-fix formatting
pnpm dev # Watch mode, rebuild on changes (tsdown)
Architecture
An MCP (Model Context Protocol) server that lets AI tools query PostgreSQL databases, optionally through an SSH tunnel. Runs over stdio transport.
Entrypoint: src/index.ts — loads env, optionally opens an SSH tunnel, creates a pg.Pool, registers MCP tools (run_query, list_schemas, list_tables, describe_table), and connects via StdioServerTransport.
Key modules:
config.ts— Zod schema (EnvSchema) for all env vars, SSH config file parser,resolveSshConfig()picks connection mode (direct / SSH config alias / explicit SSH)ssh-tunnel.ts— wrapstunnel-sshto open an SSH tunnel, returnsTunnelInfowith local portdatabase.ts—pg.Poolcreation, query execution helpers.runQueryenforces read-only viaBEGIN TRANSACTION READ ONLY+ROLLBACKsql-validator.ts— AST-level query validation usingpgsql-parser/@pgsql/traverse. In read-only mode: allowlistsSelectStmt/ExplainStmt, walks AST for hidden mutations (CTE DML,SELECT INTO, locking clauses). Always enforces single-statement limitutil.ts— readspackage.jsonfor project name/version
Three SSH connection modes (determined by env vars):
- Direct — no SSH vars → connect to Postgres directly
- SSH config —
SSH_HOSTset → parse~/.ssh/configfor that alias - Explicit SSH —
SSH_HOSTNAME+SSH_USER→ use env vars directly
Code Style
- Prettier with
printWidth: 90 - ESM (
"type": "module") — use.jsextensions in imports even for.tsfiles - TypeScript strict mode with
noUnusedLocalsandnoUnusedParameters
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.
- 3d ago First seen · 57 lines · 752 tokens per session scan A cdce6831ec19
postgres-ssh-mcp CLAUDE.md is an instructions file published in the GitHub repository SecretX33/postgres-ssh-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 752 tokens to every session, about $0.0038 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 2026-08-31.
Other instructions, from other repositories
supabase copilot-instructions.md
Copilot instructions for supabase/supabase, covering copilot code review instructions, review policy — read this first, confidence threshold, what not to comment on and what to comment on (priority order).
prest copilot-instructions.md
Copilot instructions for prest/prest, covering copilot instructions for prest go backend, project scope, core engineering principles, solid principles for go and s — single responsibility.
MCP-PostgreSQL-Ops copilot-instructions.md
Instructions for call518/MCP-PostgreSQL-Ops, covering architecture overview, core components, key patterns, in functions.py and development workflows.
postgres-skills AGENTS.md
Instructions for neondatabase/postgres-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.
pg_exporter AGENTS.md
Instructions for nbari/pg_exporter, covering agents.md, project shape, first steps, devpod workflow (preferred) and local commands.
counterpoise-ledger CLAUDE.md
Instructions for jeffjjohnston/counterpoise-ledger, covering claude.md, project overview, development commands, essential commands and testing.