agentpg CLAUDE.md

agentpg CLAUDE.md is an instructions file for coding agents from youssefsiam38/agentpg. It costs 11,693 tokens per session, scanned A, original, MPL-2.0.

Instructions for AgentPG, an event-driven Go framework for running AI agents asynchronously. It uses PostgreSQL, a database, to store state and coordinate workers, and connects to Claude's batch service.

In plain words
What is it for?
Use it when building or changing AgentPG services, including workers, sessions, runs, tools, database state, and batch processing.
Why use it?
It explains how the framework is structured and how agents can keep working safely across multiple workers.

Instructions file

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 instructions/youssefsiam38/agentpg/claude-md
Clone the repo
git clone --depth 1 https://github.com/youssefsiam38/agentpg

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 agentpg CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/youssefsiam38/agentpg/claude-md.svg)](https://agentmods.dev/instructions/youssefsiam38/agentpg/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/youssefsiam38/agentpg/claude-md"><img src="https://agentmods.dev/badge/instructions/youssefsiam38/agentpg/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 11,693 This file is loaded in full into every session.
When invoked 11,693 The same file — it is already loaded in full.
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 $0.11693 $0.11693
Opus 5 $0.05847 $0.05847
Sonnet 5 $0.02339 $0.02339
Haiku 4.5 $0.01169 $0.01169

Measured 4d ago against content hash 80bcee10c64c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentpg 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 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.

CLAUDE.md · 1,285 lines

How it starts

The opening of the file, as written. The whole thing — 1,285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentPG - Event-Driven AI Agent Framework

Event-driven Go framework for building async AI agents using PostgreSQL for state management and distribution. Provides stateful, distributed, and transaction-safe agent execution with Claude Batch API integration.

Architecture Overview

AgentPG Architecture

Layer 1: HTTP Server Layer (Optional)

  • ui.UIHandler() - /ui/* (HTMX + SSR)
  • Components: Dashboard, Sessions/Runs, Chat Interface, Monitoring

Layer 2: Workers

  • Client 1 (Worker), Client 2 (Worker), Client N (Worker)
  • Deployed as k8s pods

Layer 3: PostgreSQL Database

  • Tables: Sessions, Runs, Iterations, Tools, Messages, Instances, Agents
  • LISTEN/NOTIFY channels:
    • agentpg_run_created
    • agentpg_tool_pending
    • agentpg_run_state
    • agentpg_tools_complete

Layer 4: Claude Batch API

  • 24h processing window
  • Async submission/polling

Key Design Principles

  1. PostgreSQL as Single Source of Truth: All state stored in PostgreSQL. No in-memory state that could be lost.
  2. Event-Driven with Polling Fallback: Uses LISTEN/NOTIFY for real-time events, with polling as fallback.
  3. Race-Safe Distribution: Uses SELECT FOR UPDATE SKIP LOCKED for safe work claiming across workers.
  4. Transaction-First: RunTx() accepts user transactions for atomic operations.
  5. Database-Driven Agents: Agents are database entities with UUID primary keys, not per-client registrations. Tools are registered per-client.
  6. Multi-Level Agent Hierarchies: Agents can be tools for other agents (PM → Lead → Worker pattern).

Core Concepts

Client

A Client represents a single worker instance. Multiple clients can run across different processes/pods, sharing work from the same database.

client, err := agentpg.NewClient(driver, &agentpg.ClientConfig{
    APIKey: os.Getenv("ANTHROPIC_API_KEY"),
    Name:   "worker-1",
})

Agent

An Agent is a Claude-powered AI with a specific role, model, and system prompt. Agents are database entities identified by UUID, created via CreateAgent() after the client starts.

agent, err := client.CreateAgent(ctx, &agentpg.AgentDefinition{
    Name:         "assistant",
    Model:        "claude-sonnet-4-5-20250929",
    SystemPrompt: "You are a helpful assistant.",
})
// Use agent.ID (uuid.UUID) when running

Read the full file on GitHub · 1,285 lines

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. 4d ago First seen · 1,285 lines · 11,693 tokens per session scan A 80bcee10c64c

Subscribe to this mod's changes

agentpg CLAUDE.md is an instructions file published in the GitHub repository youssefsiam38/agentpg (11 stars, last pushed 5mo ago), licensed MPL-2.0. It adds 11,693 tokens to every session, about $0.0585 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 2026-08-30.