agent-db

agent-db is a skill for Claude Code, Codex from prebid/salesagent. It costs 43 tokens per session (503 once invoked), scanned A, original, Apache-2.0.

Start an isolated PostgreSQL container for integration testing. Each worktree gets its own container on a unique port — no mutex, no conflicts. Use this before running integration tests in a worktree agent.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/prebid/salesagent/agent-db
Any agent
npx skills add prebid/salesagent --skill agent-db
Clone the repo
git clone --depth 1 https://github.com/prebid/salesagent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agent-db

README.md
[![agentmods](https://agentmods.dev/badge/skills/prebid/salesagent/agent-db.svg)](https://agentmods.dev/skills/prebid/salesagent/agent-db)
Your own site
<a href="https://agentmods.dev/skills/prebid/salesagent/agent-db"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/agent-db.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00503
Opus 5 $0.00022 $0.00251
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00004 $0.00050

Measured 2d ago against content hash 3450285cd27f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-db 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.

The scan reads SKILL.md. This mod also ships 1 executable file (agent-db.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/agent-db/SKILL.md · 66 lines

What it actually says

Agent Database

Starts a lightweight postgres:17-alpine container scoped to the current worktree. The container name is deterministic (agent-pg-<dirname>), so up/down/status work across calls without tracking state manually.

When to use

  • Before running integration tests in a worktree agent
  • When you need a private Postgres that won't conflict with other agents
  • Instead of make test-stack-up (which starts the full docker-compose stack)

Setup

eval $(.claude/skills/agent-db/agent-db.sh up)

This exports:

  • DATABASE_URL — points to your private Postgres
  • ADCP_TESTING=true
  • ENCRYPTION_KEY, GEMINI_API_KEY — test defaults

The integration_db pytest fixture handles the rest: creates per-test databases, runs Base.metadata.create_all(), cleans up after each test.

Running tests

# Integration tests (real Postgres)
uv run pytest tests/integration/ -x -q

# Targeted
uv run pytest tests/integration/test_specific.py -x -q -k "test_name"

# Unit tests (no DB needed)
uv run pytest tests/unit/ -x -q

Commands

Command Effect
eval $(.claude/skills/agent-db/agent-db.sh up) Start container, export env vars
.claude/skills/agent-db/agent-db.sh down Stop and remove container
.claude/skills/agent-db/agent-db.sh status Check if running

Idempotent

Running up when already running re-exports the same env vars (same port, same container). Safe to call multiple times.

Cleanup

The container is removed when you run down or when the worktree is deleted. If the worktree is cleaned up without running down, the container stays orphaned — run docker rm -f agent-pg-<worktree-name> to clean it up.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 66 lines · 43 tokens per session scan A 3450285cd27f

Subscribe to this mod's changes

agent-db is a skill published in the GitHub repository prebid/salesagent (36 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 503 once invoked, about $0.0002 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 2026-09-01.

Related

Other skills, from other repositories

safe-sql-execution

Use whenever code will build, return, fetch, or execute SQL that runs against a user's real Postgres database — even when the request reads like an ordinary feature or bug fix and never says "security," "injection," or "SafeSqlFragment." This covers: writing or editing any pg-meta function, query builder, or endpoint…

supabase/supabase · 221 tokens

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 …

garrytan/gbrain · 96 tokens

postgres-adopt

Detect which gbrain engine is in use (PGLite vs Postgres), prefer Postgres for agent-harness installs, install/provision Postgres (Supabase discovery via SUPABASEACCESSTOKEN, local Postgres, opt-in Docker), and move an existing PGLite brain with the guarded engine migration. Detection is one engine-free command; the…

garrytan/gbrain · 85 tokens

amazon aurora dsql

Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.

awslabs/mcp · 46 tokens

claimable-postgres

Provision instant temporary Postgres databases via Claimable Postgres by Neon (neon.new) with no login, signup, or credit card. Supports REST API, CLI, and SDK. Use when users ask for a quick Postgres environment, a throwaway DATABASEURL for prototyping/tests, or "just give me a DB now". Triggers include: "quick…

neondatabase/mcp-server-neon · 123 tokens

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, FK…

awslabs/agent-plugins · 227 tokens