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/jpka/sw-postgres-mcp/agents-mdgit clone --depth 1 https://github.com/jpka/sw-postgres-mcpWhat 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 | $0.00176 | $0.00176 |
| Opus 5 | $0.00088 | $0.00088 |
| Sonnet 5 | $0.00035 | $0.00035 |
| Haiku 4.5 | $0.00018 | $0.00018 |
Grade A, and why
sw-postgres-mcp 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 2d 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.
What it actually says
sw-postgres-mcp
A safe-write Postgres MCP server: an agent can read and modify a database without being able to cause an unrecoverable accident. The differentiator is the safety layer, not the tool coverage.
See mcp-postgres-build-plan.md for the full build plan.
Agent skills
Issue tracker
Issues live in this repo's GitHub Issues, driven by the gh CLI. See docs/agents/issue-tracker.md.
Triage labels
The five canonical triage roles, each label string equal to its name. See docs/agents/triage-labels.md.
Domain docs
Single-context — one CONTEXT.md and docs/adr/ at the repo root. See docs/agents/domain.md.
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.
- 2d ago First seen · 20 lines · 176 tokens per session scan A 10c541b80f14
sw-postgres-mcp AGENTS.md is an instructions file published in the GitHub repository jpka/sw-postgres-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 176 tokens to every session, about $0.0009 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
expense-budget-tracker AGENTS.md
Instructions for kirill-markin/expense-budget-tracker, covering expense-budget-tracker, rules, components, supported clients and key paths.
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.
db-connect-mcp CLAUDE.md
Instructions for yugui923/db-connect-mcp, covering claude.md, project overview, pre-commit requirements, 1. format code and 2. lint code.
Synapsor-Runner AGENTS.md
Instructions for Synapsor/Synapsor-Runner, covering agent guide for synapsor runner, first commands, what not to change casually, how the flow works and add a capability without reading dist/.
ai-dba-workbench CLAUDE.md
Claude Code instructions for pgEdge/ai-dba-workbench, covering claude standing instructions, primary agent role, trivial-edit carve-out, project structure and key files.