sell

A guide for offering services through paid HTTP access using x402, a payment method for machine-to-machine web requests, and ServiceOffer resources.

In plain words
What is it for?
Use it to create, list, inspect, wait for, or delete payment-gated services, including model inference, HTTP services, and fine-tuning services.
Why use it?
It removes the need to design the payment route, service description, and status-checking steps from scratch when exposing a service.

Skill for Claude CodeCodex

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 skills/obolnetwork/obol-stack/sell
Any agent
npx skills add ObolNetwork/obol-stack --skill sell
Clone the repo
git clone --depth 1 https://github.com/ObolNetwork/obol-stack

Made for: Claude Code, Codex.

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,235 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00103 $0.01235
Opus 5 $0.00051 $0.00617
Sonnet 5 $0.00021 $0.00247
Haiku 4.5 $0.00010 $0.00123

Measured 3d ago against content hash d358efc754d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sell 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/monetize.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

internal/embed/skills/sell/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sell

Sell access to services via ServiceOffer custom resources. Each ServiceOffer describes a service to expose publicly with x402 micropayments (USDC via EIP-3009 or OBOL via Permit2, selected with --token). The cluster's serviceoffer-controller performs reconciliation; monetize.py process now waits for controller convergence and refreshes /skill.md.

When to Use

  • Exposing a local Ollama model for paid inference
  • Creating payment-gated routes for any upstream service
  • Checking the status of monetized services
  • Listing or deleting existing service offers
  • Processing pending offers that haven't been fully reconciled

When NOT to Use

  • Read-only Ethereum queries — use ethereum-networks
  • Signing transactions — use ethereum-local-wallet
  • Cluster diagnostics — use obol-stack

Quick Start

# List all service offers across namespaces
python3 scripts/monetize.py list

# Create a new offer to monetize a local Ollama model
python3 scripts/monetize.py create my-inference \
  --model qwen3.5:9b \
  --runtime ollama \
  --upstream ollama \
  --namespace llm \
  --port 11434 \
  --per-request 0.001 \
  --network base-sepolia \
  --pay-to 0xYourWalletAddress

# Check status of an offer
python3 scripts/monetize.py status my-inference --namespace llm

# Process all pending offers (waits for controller convergence)
python3 scripts/monetize.py process --all

# Process a single offer
python3 scripts/monetize.py process my-inference --namespace llm

# Delete an offer (cascades Middleware + HTTPRoute via OwnerRef)
python3 scripts/monetize.py delete my-inference --namespace llm

Commands

Command Description
list List all ServiceOffer CRs across namespaces
status <name> --namespace <ns> Show conditions and endpoint for one offer
create <name> --model ... --namespace ... Create a new ServiceOffer CR
process <name> --namespace <ns> Wait for a single offer to converge
process --all Wait for all non-Ready offers to converge
delete <name> --namespace <ns> Delete an offer and its owned resources

Read the full file on GitHub · 119 lines

Files

What ships with it

4 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.

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 · 119 lines · 103 tokens per session scan A d358efc754d4

Subscribe to this mod's changes

sell is a skill published in the GitHub repository ObolNetwork/obol-stack (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,235 once invoked, about $0.0005 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.