Obolus: Instructions file for Claude Code

CLAUDE.md

Obolus CLAUDE.md is an instructions file for Claude Code from inviti8/Obolus. It costs 3,179 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for Claude Code about Obolus, an MCP server that gives an AI agent a temporary Algorand wallet. Algorand is a blockchain network, and MCP is a way to provide tools to an AI assistant.

In plain words
What is it for?
Use it when building or maintaining Obolus, paying for x402-protected web resources, or checking its distinction from the Authen reference integration.
Why use it?
It gives the agent the background needed to handle x402 payments correctly. x402 is a web payment method where a server requests payment before returning a resource.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: positional $N argument.

This is inviti8/Obolus's own configuration. It tells Claude Code how to work on Obolus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Obolus configures →

Reuse

Borrowing it

Nothing to install: this file belongs to inviti8/Obolus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/inviti8/Obolus/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/inviti8/Obolus

Made for: Claude Code.

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 Obolus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inviti8/obolus/claude-md.svg)](https://agentmods.dev/instructions/inviti8/obolus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/inviti8/obolus/claude-md"><img src="https://agentmods.dev/badge/instructions/inviti8/obolus/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,179 This file is loaded in full into every session.
When invoked 3,179 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03179 $0.03179
Opus 5 $0.01589 $0.01589
Sonnet 5 $0.00636 $0.00636
Haiku 4.5 $0.00318 $0.00318

Measured 2d ago against content hash b7ae17a92e2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Obolus 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 2d 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 · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obolus — agent brief

An MCP server that gives an AI agent a disposable Algorand wallet, so it can pay for x402 resources without a human provisioning anything.

The name is the coin paid to the ferryman for passage: a small denomination, one purpose, spent and gone.

What Obolus is, and is not

Is: a general-purpose x402 payment client exposed over the Model Context Protocol. Give it a URL that answers 402, and it pays and returns the body.

Is not: a client for Authen. Authen is the reference integration and nothing more. This distinction is load-bearing — see "Why not just an Authen client" below.

Why this exists — the measured problem

Field data pulled live from the GoPlausible facilitator on 2026-08-12 (re-measure before trusting; it moves weekly):

Metric Value
Resources listed in the Bazaar 1,204
Merchants 53
Settlements 288,110
Volume $22,447
"Unique payers" 450
Payers accounting for 90% of volume 13
Top payer's share 36%

The top four payers made 77,217 / 36,322 / 29,854 / 14,857 settlements at exactly $0.10 each. Those are scripted loops against known endpoints, not agents shopping.

Two further findings, both verified rather than inferred:

  • Top-earning merchants are not in the Bazaar discovery index at all. Their payTo addresses do not appear among the ~80 in /discovery/resources. So discovery is not what drives purchases; pre-arranged integrations are.
  • A listed payTo with several resources had received $0.00, ever. Listing well brings nothing.

The conclusion that matters: x402 has no buyer-side infrastructure. A payment requires an Algorand account, a USDC opt-in, a funded balance and transaction signing. No agent framework ships any of that. The rail exists; nothing can reach it.

That is the gap Obolus fills. It is also why this is a better product than another endpoint — the ecosystem has 1,204 sellers and approximately zero buyers.

Read the full file on GitHub · 230 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. 2d ago Changed · +15 lines · +238 tokens per session b7ae17a92e2c
  2. 6d ago First seen · 215 lines · 2,941 tokens per session scan A 1a482841526a

Subscribe to this mod's changes

Obolus CLAUDE.md is an instructions file published in the GitHub repository inviti8/Obolus (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 3,179 tokens to every session, about $0.0159 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens