agentmods.dev

ddg-agent-payable-services AGENTS.md

ddg-agent-payable-services AGENTS.md is an instructions file for Codex, OpenCode from daedalusdevelopmentgroup/ddg-agent-payable-services. It costs 635 tokens per session, scanned A, original, MIT.

Repository instructions for using DDG Agent-Payable Services, a gateway where AI agents can call utilities, blockchain services, market-data tools, security audits, and language models. Calls may use x402, a payment method for sending USDC on the Base blockchain.

In plain words
What is it for?
Helping an agent connect to DDG through an MCP server or Python package, inspect available services, and make free or paid calls with a funded Base USDC key.
Why use it?
They give an AI agent the setup details, service addresses, package commands, and payment rules needed to discover and call the gateway’s services.

Instructions file for CodexOpenCode

not rated 0 17d ago A scan 635 tokens original MIT
View the source file daedalusdevelopmentgroup/ddg-agent-payable-services
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/daedalusdevelopmentgroup/ddg-agent-payable-services/agents-md
Clone the repo
git clone --depth 1 https://github.com/daedalusdevelopmentgroup/ddg-agent-payable-services

Made for: Codex, OpenCode.

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 ddg-agent-payable-services AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daedalusdevelopmentgroup/ddg-agent-payable-services/agents-md.svg)](https://agentmods.dev/instructions/daedalusdevelopmentgroup/ddg-agent-payable-services/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/daedalusdevelopmentgroup/ddg-agent-payable-services/agents-md"><img src="https://agentmods.dev/badge/instructions/daedalusdevelopmentgroup/ddg-agent-payable-services/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 635 This file is loaded in full into every session.
When invoked 635 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 $0.00635 $0.00635
Opus 5 $0.00318 $0.00318
Sonnet 5 $0.00127 $0.00127
Haiku 4.5 $0.00064 $0.00064

Measured 3d ago against content hash 3ddca3db1ad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ddg-agent-payable-services 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.

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — DDG Agent-Payable Services

This file helps AI agents (Cursor, Claude Code, autonomous agents) discover and use DDG.

What this is: a pay-per-call gateway for AI agents. One entry point (https://agents.daedalusdevelopmentgroup.com) exposing 90+ callable tools — utilities, blockchain RPC, market data, security audits — plus an OpenAI-compatible LLM gateway. Payment is x402 (USDC on Base); most routes grant free-trial calls per agent (no wallet needed to start).

Use it in 30 seconds

MCP (Claude/Cursor/Cline) — remote, no install:

https://mcp.daedalusdevelopmentgroup.com/mcp   (streamable-http)

Or via the registry: io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp.

Python:

pip install "ddg-agent-services-mcp[openai]"

from ddg_agent_services_mcp import ddg, create_openai_client
ddg(agent_id="my-agent", private_key="0x"+"1"*64).get("/v1/model-catalog")  # free
# paid/metered auto-pays x402 with a funded Base USDC key:
create_openai_client(agent_id="my-agent", private_key="0x<funded>").chat.completions.create(
    model="glm-4.5-air", messages=[{"role":"user","content":"hi"}])

OpenAI SDK drop-in (any language): point base_url at https://agents.daedalusdevelopmentgroup.com/v1. GET /v1/models is free; POST /v1/chat/completions is metered (from $0.0002/call) and returns 402 until an x402 payment header is attached.

TypeScript client: clients/typescript/ (uses x402-fetch + viem).

Discovery documents

  • GET /openapi.json — full API
  • GET /llms.txt — human/agent-readable overview
  • GET /.well-known/x402 — x402 payment manifest
  • GET /.well-known/ddg-agent-pricing.json — per-route pricing
  • GET /v1/model-catalog — model tiers + prices (free)

Working in this repo

  • src/ddg_agent_services_mcp/ — MCP server + client (tools.py: DDGPaidClient, create_openai_client, ddg).
  • clients/typescript/ — TS drop-in client (npm i then npm run typecheck).
  • examples/ — runnable quickstarts (quickstart_python.py, bazaar_list.py).
  • server.json — MCP registry manifest (published via .github/workflows/publish-mcp.yml).
  • Build/publish Python: uv build && uv publish. See QUICKSTART.md.

Read the full file on GitHub · 51 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. 3d ago First seen · 51 lines · 635 tokens per session scan A 3ddca3db1ad9

Subscribe to this mod's changes

ddg-agent-payable-services AGENTS.md is an instructions file published in the GitHub repository daedalusdevelopmentgroup/ddg-agent-payable-services (0 stars, last pushed 17d ago), licensed MIT. It adds 635 tokens to every session, about $0.0032 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.

Finance and fintechWeb3 and blockchainagent-commerceai-agentsmachine-paymentsmcpopenapi
Related

Other instructions, from other repositories

gmgn-skills CLAUDE.md

Instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.

GMGNAI/gmgn-skills · 2,591 tokens

mercato-dapp AGENTS.md

Instructions for mercato-supply-chain/mercato-dapp, covering mercato — agent guide, quick facts, documentation map, domain glossary and user roles.

mercato-supply-chain/mercato-dapp · 3,830 tokens

lightning-enable-mcp CLAUDE.md

Instructions for refined-element/lightning-enable-mcp, covering claude.md — lightning enable mcp, project overview, bug fix workflow and engineering standards.

refined-element/lightning-enable-mcp · 514 tokens

x402-stellar-kit AGENTS.md

AGENTS.md instructions for CodeStrux/x402-stellar-kit, covering working with x402-stellar-kit, the one invariant, production seams, bootstrapping accounts across a custody boundary and add x402 to an existing api.

CodeStrux/x402-stellar-kit · 3,410 tokens

cryptopilot-mcp CLAUDE.md

Claude Code instructions for cryptopilot-tools/cryptopilot-mcp, covering claude.md, project, stack, architecture and mcp tools (5).

cryptopilot-tools/cryptopilot-mcp · 1,640 tokens

tm-mcp-server CLAUDE.md

Claude Code instructions for jun229/tm-mcp-server, covering claude.md, project overview, architecture, key design decision: quote caching and tools (8 total).

jun229/tm-mcp-server · 795 tokens