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/tendant/postgres-mcp-go/agents-mdgit clone --depth 1 https://github.com/tendant/postgres-mcp-goWrote 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/tendant/postgres-mcp-go/agents-md)<a href="https://agentmods.dev/instructions/tendant/postgres-mcp-go/agents-md"><img src="https://agentmods.dev/badge/instructions/tendant/postgres-mcp-go/agents-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 | $0.00576 | $0.00576 |
| Opus 5 | $0.00288 | $0.00288 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
postgres-mcp-go AGENTS.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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- Module name is
github.com/tendant/postgres-mcp-go; keep imports aligned with it. - Place runnable entry points under
cmd/(e.g.,cmd/agent/main.go) and reusable packages underinternal/orpkg/. - Store SQL fixtures, migrations, or prompt templates in
assets/, and environment samples inconfigs/. - Use
testdata/for deterministic fixtures; it is automatically ignored by Go tools. - Keep generated binaries, coverage files, and local
.envsecrets out of version control (already covered in.gitignore).
Build, Test, and Development Commands
make build— compiles and dropsbin/postgres-mcpwith sandboxed Go caches.make test— runsgo test ./...with the same cached toolchain setup.make run-stdio— launches the MCP server over stdio (requiresDATABASE_URL).make run-http— launches the HTTP server; add flags viaEXTRA_FLAGS(e.g.,--http-json).go mod tidy— normalize module manifests after dependency changes.go fmt ./...— format code using Go defaults.
Coding Style & Naming Conventions
- Follow Go 1.24 defaults: tabs for indentation, one statement per line, no unnecessary semicolons.
- Use concise, lowercase package names (
postgres,agent) and PascalCase for exported types and functions. - Prefix sentinel errors with
Errand wrap upstream errors with%wto preserve context. - Document exported identifiers with complete sentences so
godocoutput stays clear.
Testing Guidelines
- Organize tests as table-driven cases in
*_test.gofiles colocated with the code they cover. - Prefer standard library
testingplustestdata/fixtures; add integration tests underinternal/<pkg>/integration_test.gowhen needed. - Maintain at least 80% package coverage; verify with
go test -cover ./...before opening a PR.
Commit & Pull Request Guidelines
- Write imperative, 1-line commit subjects similar to the existing history (
add go.mod). - Squash unrelated work; each commit should build and pass tests.
- PR descriptions must include the problem statement, the solution outline, and local command output (
go test ./...). - Link issues with
Fixes #123orRefs #123, and request review only after CI succeeds.
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 · 38 lines · 576 tokens per session scan A 3fb85f4bc3a0
postgres-mcp-go AGENTS.md is an instructions file published in the GitHub repository tendant/postgres-mcp-go (2 stars, last pushed 11mo ago), licensed MIT. It adds 576 tokens to every session, about $0.0029 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
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.
counterpoise-ledger CLAUDE.md
Instructions for jeffjjohnston/counterpoise-ledger, covering claude.md, project overview, development commands, essential commands and testing.
tiger-slack CLAUDE.md
Instructions for timescale/tiger-slack, covering tiger slack - ai-powered slack analytics platform, architecture overview, development commands, service management and database access.
bun-pg-mcp AGENTS.md
AGENTS.md instructions for igoraguiar/bun-pg-mcp, covering agents.md, project context, tech stack, directory map and commands.
mcp-database CLAUDE.md
Claude Code instructions for DiegoBulhoes/mcp-database, covering claude.md, commands, architecture, invariants (do not weaken) and adding or changing a tool.
tai42-mcp-dynamic-postgres AGENTS.md
AGENTS.md instructions for tai42ai/tai42-mcp-dynamic-postgres, covering agents.md, commits, build, test, lint, comments and docs and rules.