integrate-seatlayer

integrate-seatlayer is a skill for Claude Code, Codex from seatlayer/seatlayer-ai-toolkit. It costs 98 tokens per session (1,504 once invoked), scanned A, original, MIT.

A guide for adding or reviewing SeatLayer in an existing application, where SeatLayer can provide hosted booking, seat selection, checkout, or private buyer access. It first studies the repository and uses SeatLayer’s current documentation to choose an integration approach.

In plain words
What is it for?
Use it to install or verify hosted booking, embeds, seat pickers, buyer or mobile software development kits, server integrations, custom checkout, holds, private sales, and partner access.
Why use it?
It prevents a booking system from duplicating responsibilities already owned by the application or SeatLayer. It also helps protect server-only credentials, payment data, booking references, inventory, and private access information.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the seatlayer plugin — 1 skill, 4 commands, 1 MCP server shipped together

Good fit Use it to install or verify hosted booking, embeds, seat pickers, buyer or mobile software development kits, server integrations, custom checkout, holds, private sales, and partner access.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seatlayer/seatlayer-ai-toolkit/integrate-seatlayer
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 seatlayer/seatlayer-ai-toolkit --skill integrate-seatlayer
Clone the repo
git clone --depth 1 https://github.com/seatlayer/seatlayer-ai-toolkit

Made for: Claude Code, Codex.

Or install seatlayer, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 1 MCP server.

Its marketplace also offers this one on its own, as the plugin seatlayer/plugin install seatlayer after adding the marketplace above.

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 integrate-seatlayer

README.md
[![agentmods](https://agentmods.dev/badge/skills/seatlayer/seatlayer-ai-toolkit/integrate-seatlayer.svg)](https://agentmods.dev/skills/seatlayer/seatlayer-ai-toolkit/integrate-seatlayer)
Your own site
<a href="https://agentmods.dev/skills/seatlayer/seatlayer-ai-toolkit/integrate-seatlayer"><img src="https://agentmods.dev/badge/skills/seatlayer/seatlayer-ai-toolkit/integrate-seatlayer.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,504 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.
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 $0.00098 $0.01504
Opus 5 $0.00049 $0.00752
Sonnet 5 $0.00020 $0.00301
Haiku 4.5 $0.00010 $0.00150

Measured 7d ago against content hash 69d65f543ae0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

integrate-seatlayer 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/doctor.mjs), 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.

skills/integrate-seatlayer/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate SeatLayer

Use the live SeatLayer Markdown documentation as the product source of truth. Adapt SeatLayer to the repository; do not generate a parallel demo application unless the user explicitly asks for one.

Start with repository discovery

  1. Read repository agent instructions and contribution guidance.

  2. Inspect the package manager, framework, routing, server/client boundary, authentication, tenant model, order/payment flow, environment validation, HTTP conventions, tests, analytics adapter, and deployment platform.

  3. Determine whether SeatLayer managed ticketing or the host platform owns payment, commercial orders, tickets, refunds, and fulfilment.

  4. Run the read-only doctor when Node.js is available:

    node <skill-root>/scripts/doctor.mjs <repository-root>
    
  5. State the chosen commerce profile, SeatLayer surface, and discovered host locations before editing.

  6. Ask only for business decisions that cannot be discovered safely.

Read references/integration-map.md to select the surface and documentation routes. Read references/safety-contract.md before changing checkout, credential, booking, inventory, or webhook code.

Load focused live documentation

Always begin with:

  • https://docs.seatlayer.io/llms.txt
  • the task-specific Markdown routes selected from integration-map.md

Prefer /<page>/index.md routes. Use https://docs.seatlayer.io/llms-full.txt only when the task genuinely spans several product surfaces. Do not invent SDK methods, fields, endpoints, error codes, or release status from memory.

If live documentation conflicts with this skill, follow the live documentation and report the discrepancy.

Choose the smallest complete integration

Choose the commerce profile first:

  • Managed ticketing when SeatLayer owns hosted checkout, Orders, tickets, delivery, refunds, and Door. Use a Hosted Event Page, managed embed, or Organizer Website. Do not add a host booking endpoint.
  • Platform/custom commerce when the host owns payment, orders, tickets, refunds, and fulfilment. Use SeatPicker for checkout handoff or SeatingChart for headless selection, then book from a trusted server.
  • Private or partner distribution when access is limited by allocation. Choose a hosted access link or an origin-bound buyer access session based on the live channel contract; private means no public link, not disabled inventory.

Read the full file on GitHub · 165 lines

Files

What ships with it

6 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. 7d ago First seen · 165 lines · 98 tokens per session scan A 69d65f543ae0

Subscribe to this mod's changes

integrate-seatlayer is a skill published in the GitHub repository seatlayer/seatlayer-ai-toolkit (2 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 1,504 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 2026-08-31.