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 skills/youssefsiam38/agentpg-skill/agentpgnpx skills add youssefsiam38/agentpg-skill --skill agentpggit clone --depth 1 https://github.com/youssefsiam38/agentpg-skillWrote 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/skills/youssefsiam38/agentpg-skill/agentpg)<a href="https://agentmods.dev/skills/youssefsiam38/agentpg-skill/agentpg"><img src="https://agentmods.dev/badge/skills/youssefsiam38/agentpg-skill/agentpg.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 | $0.00078 | $0.02931 |
| Opus 5 | $0.00039 | $0.01465 |
| Sonnet 5 | $0.00016 | $0.00586 |
| Haiku 4.5 | $0.00008 | $0.00293 |
Grade C, and why
agentpg scanned grade C with 1 finding 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
// Override system prompt for this run How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentPG
Event-driven Go framework for async AI agents using PostgreSQL for state management. Source at /home/youssef/projects/agentpg.
Workflow Decision Tree
- New project setup? -> See "Quick Start" below
- Adding tools? -> See references/tools.md
- MCP server tools? -> See references/mcp.md
- Agent hierarchies? -> See references/agents.md
- Cancel or regenerate runs? -> See "Cancel and Regenerate" below
- Tool call visibility / callbacks? -> See "Tool Call Visibility" below
- Distributed workers / transactions / compaction / UI? -> See references/advanced.md
Quick Start
Prerequisites
go get github.com/youssefsiam38/agentpg
go get github.com/youssefsiam38/agentpg/driver/pgxv5 # or driver/databasesql
# Optional: go get github.com/youssefsiam38/agentpg/mcp # MCP server tools
psql $DATABASE_URL -f storage/migrations/001_agentpg_migration.up.sql
Minimal Application
package main
import (
"context"
"fmt"
"log"
"os"
"github.com/jackc/pgx/v5/pgxpool"
"github.com/youssefsiam38/agentpg"
"github.com/youssefsiam38/agentpg/driver/pgxv5"
)
func main() {
ctx := context.Background()
pool, _ := pgxpool.New(ctx, os.Getenv("DATABASE_URL"))
defer pool.Close()
client, _ := agentpg.NewClient(pgxv5.New(pool), &agentpg.ClientConfig{
APIKey: os.Getenv("ANTHROPIC_API_KEY"),
})
client.Start(ctx)
defer client.Stop(context.Background())
agent, _ := client.GetOrCreateAgent(ctx, &agentpg.AgentDefinition{
Name: "assistant",
Model: "claude-sonnet-4-5-20250929",
SystemPrompt: "You are a helpful assistant.",
})
sessionID, _ := client.NewSession(ctx, nil, nil)
response, _ := client.RunFastSync(ctx, sessionID, agent.ID, "Hello!", nil)
fmt.Println(response.Text)
}
Lifecycle Order
RegisterTool()- before Startagentmcp.RegisterServer()- MCP tools, before Start (optional)client.Start(ctx)- starts background servicesCreateAgent()/GetOrCreateAgent()- after Start (agents are DB entities)NewSession()->Run*()/RunFast*()- execute workclient.Stop(ctx)- graceful shutdown
What ships with it
12 files 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.
- references/advanced.md 7.7 KB
- references/agents.md 5.3 KB
- references/examples-agents.md 16 KB
- references/examples-basic.md 16 KB
- references/examples-cancel.md 2.8 KB
- references/examples-compaction.md 16 KB
- references/examples-retry.md 17 KB
- references/examples-tool-calls.md 5.2 KB
- references/examples-tools.md 19 KB
- references/examples-ui.md 14 KB
- references/mcp.md 5.2 KB
- references/tools.md 7.4 KB
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 · 303 lines · 78 tokens per session scan C f4fddf30cbff
agentpg is a skill published in the GitHub repository youssefsiam38/agentpg-skill (5 stars, last pushed 6mo ago), licensed MPL-2.0. It adds 78 tokens to every session and 2,931 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
studio-e2e-tests
Write and run Playwright E2E tests for Supabase Studio (e2e/studio). Use when asked to run e2e tests, write new E2E tests, or debug flaky or failing Playwright tests. Covers running commands, avoiding race conditions, waiting strategies, selectors, helper functions, and CI vs local differences.
studio-queries
React Query conventions for data fetching in Supabase Studio. Use when writing or reviewing query hooks, mutation hooks, or query keys in apps/studio/data/ — including adding the first fetch or mutation for a new API endpoint or resource. Covers queryOptions pattern, keys.ts structure, mutation hook template, and…
upgrading-chart
Upgrades Helm chart dependencies (PostgreSQL, Vault) in the Chainloop project, including vendorized charts, container images, and CI/CD workflows. Use when the user mentions upgrading Helm charts, Bitnami dependencies, PostgreSQL chart, or Vault chart. CRITICAL - Major version upgrades are FORBIDDEN and must be…
payload-cms
Install and wire Payload CMS into this Next.js 16 app, backed by Supabase Postgres and Supabase Storage — packages, payload.config.ts, the (payload) route group, collections derived from the actual page views, type generation, migrations, and proving the read loop end-to-end. Use when the user asks to "add a CMS"…
dump-schema
Dump clean Postgres schema to a file and copy path to clipboard.