A development guide for adding integrations, called plugins, to the AgentPay command-line tool. It defines where shared registration, plugin commands, and plugin-specific network code belong.

Use it when adding or restructuring an integration such as Bitrefill. It covers registering the plugin, handling its API or browser code, and reusing the existing signing, policy, approval, and transaction paths.

It prevents each integration from wiring commands and payment logic differently, reducing duplicated code and misplaced responsibilities.

add-plugin — Skill for Codex by worldliberty/agentpay-sdk

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.

Any agent

npx skills add worldliberty/agentpay-sdk --skill add-plugin

Clone the repo

git clone --depth 1 https://github.com/worldliberty/agentpay-sdk

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/worldliberty/agentpay-sdk/add-plugin/github.svg)](https://agentmods.dev/skills/worldliberty/agentpay-sdk/add-plugin)

Your own site

<a href="https://agentmods.dev/skills/worldliberty/agentpay-sdk/add-plugin"><img src="https://agentmods.dev/badge/skills/worldliberty/agentpay-sdk/add-plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/worldliberty/agentpay-sdk/add-plugin"><img src="https://agentmods.dev/badge/skills/worldliberty/agentpay-sdk/add-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 817 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00097	$0.00817
Opus 5.5	$0.00039	$0.00327
Sonnet 5.5	$0.00019	$0.00163
Haiku 4.5	$0.00010	$0.00082

Measured 1mo ago against content hash a4032ca348b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-plugin 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 1mo 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.

skills/add-plugin/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Plugin

Use this skill when the task is "add another plugin like Bitrefill" or "make plugin onboarding more reusable."

Ground Truth

src/cli.ts is the main CLI entrypoint, but plugin-specific command trees should not be wired inline there.
src/plugins/types.ts defines the shared CliPluginContext and the generic plugin registrar shape.
src/plugins/index.ts is the registry for built-in plugins.
src/plugins/bitrefill.ts is the reference implementation for a plugin that owns its own command tree.
Plugin-specific HTTP or browser/bootstrap code belongs in src/lib/<plugin>.ts or src/lib/<plugin>/.
Signing, policy checks, manual approval handling, and raw transaction broadcast plumbing stay on the existing AgentPay path exposed through CliPluginContext.

Default Architecture

Create src/plugins/<plugin>.ts.
Register the plugin in src/plugins/index.ts.
Keep plugin-local API normalization, transports, cookies, scraping, or challenge handling in src/lib/<plugin>*.
Keep src/cli.ts responsible only for assembling shared dependencies and calling registerBuiltinCliPlugins(...).
Reuse context.agent.runJson(...) plus context.broadcast.* for any payment flow that reaches the daemon.

Implementation Rules

Do not add another large inline .command('<plugin>') block to src/cli.ts.
Do not reimplement signing, nonce management, or policy logic in the plugin.
If the plugin needs onchain payment, default to preview-first behavior and make live payment explicit with --broadcast.
If the plugin only needs a quote plus an optional live payment path, prefer one buy-style command over a redundant separate price command.
Keep plugin-specific error handling inside the plugin module when possible.
If a remote API needs browser bootstrap, Cloudflare handling, or cookies, isolate that behind the plugin's transport/client layer instead of leaking it into the shared CLI.
Pass only shared helpers through CliPluginContext; keep plugin business logic inside the plugin module.

Read the full file on GitHub · 59 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 452 B

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.

1mo ago First seen · 59 lines · 97 tokens per session scan A a4032ca348b1

Subscribe to this mod's changes

add-plugin is a skill published in the GitHub repository worldliberty/agentpay-sdk (461 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 817 once invoked, about $0.0004 per session on Opus 5.5. 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.

Backend and APIs agentic-payments ai-agents stablecoin

telnyx-iot-curl

Manage IoT SIM cards, eSIMs, data plans, and wireless connectivity. Use when building IoT/M2M solutions. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens

telnyx-sip-curl

Configure SIP trunking connections and outbound voice profiles. Use when connecting PBX systems or managing SIP infrastructure. This skill provides REST API (curl) examples.

team-telnyx/ai · 39 tokens

telnyx-twilio-migration

Migrate from Twilio to Telnyx. Orchestrates a complete 6-phase migration: discovery, planning, setup, code migration, validation, and cleanup. Covers voice (TwiML to TeXML, Call Control API), messaging, WebRTC, SIP trunking, verify, fax, video, IoT, number lookup, and porting. Includes automated scanners, validation…

team-telnyx/ai · 93 tokens

add-plugin