agentmods.dev

1cent AGENTS.md

Repository instructions for a pay-per-call URL intelligence service that agents access through MCP, with payments in USDC on Base, a blockchain network.

In plain words
What is it for?
Use them when changing or deploying the 1cent service, especially its MCP or REST endpoints, payment flow, database, security protections, or monitoring.
Why use it?
They keep payment handling, private keys, security checks, backups, and production deployment within the project's safety rules.

Instructions file for CodexOpenCode

0 14d ago A scan 256 tokens original Apache-2.0
View the source file maxzoa/1cent
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/maxzoa/1cent/agents-md
Clone the repo
git clone --depth 1 https://github.com/maxzoa/1cent

Made for: Codex, OpenCode.

Per session 256 This file is loaded in full into every session.
When invoked 256 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 $0.00256 $0.00256
Opus 5 $0.00128 $0.00128
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash 747fef8d7286, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

1cent 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 yesterday.

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 · 17 lines

What it actually says

1cent agent rules

  • Scope: this directory and NAS project /volume1/docker/1cent only.
  • Public production is Base Mainnet eip155:8453, Base USDC, PayAI and seller address configured by the owner. Never change those values without a new explicit owner instruction.
  • Never execute a payment merely to test deployment. Unpaid REST/MCP smoke is the default.
  • Never request, print, store or transmit buyer/seller seed phrases or private keys.
  • Buyer signing stays client-side. Seller private key must not exist on the server.
  • Before production deploy: fresh PostgreSQL backup, full checks, rollback artifact and unpaid smoke.
  • Preserve UNKNOWN no-retry, payment identifier/fingerprint idempotency, emergency pause, rate limits, concurrency, SSRF protection, monitoring and automatic rollback.
  • Never use Docker socket or global --remove-orphans; do not touch unrelated containers.
  • No web admin, browser automation, paywall/CAPTCHA bypass or access-control bypass.
  • Diagnose before patch. Keep SSRF, payment and production gates fail-closed.
  • Never expose .env, payment signatures, Telegram tokens, API tokens or private evidence in logs, Git, reports or chat.
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. yesterday First seen · 17 lines · 256 tokens per session scan A 747fef8d7286

Subscribe to this mod's changes

1cent AGENTS.md is an instructions file published in the GitHub repository maxzoa/1cent (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 256 tokens to every session, about $0.0013 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.

Backend and APIsDatabasesSecurityai-agentsbase-mainnetfastapimcpmodel-context-protocolssrf-protection
Related

Other instructions, from other repositories

mcpelevator CLAUDE.md

Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.

pacnpal/mcpelevator · 2,626 tokens

mcpelevator AGENTS.md

Instructions for pacnpal/mcpelevator, covering commands, architecture and conventions.

pacnpal/mcpelevator · 1,557 tokens

maple-procure CLAUDE.md

Claude Code instructions for samarpassey/maple-procure, covering mapleprocure, commands, read these when and repo conventions.

samarpassey/maple-procure · 675 tokens

mcp-sql-server AGENTS.md

AGENTS.md instructions for harryvaldez/mcp-sql-server, covering agents, project snapshot, fast start, architecture boundaries and non-negotiable guardrails.

harryvaldez/mcp-sql-server · 631 tokens

reed AGENTS.md

AGENTS.md instructions for simonives/reed, covering reed — agent context, scope, precedence, instructions and conventions.

simonives/reed · 2,930 tokens

reed CLAUDE.md

Claude Code instructions for simonives/reed, covering reed — claude context, scope, precedence, instructions and conventions.

simonives/reed · 2,832 tokens