Borrowing it
Nothing to install: this file belongs to xsolla/xsolla-ai-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xsolla/xsolla-ai-kit/main/CLAUDE.mdgit clone --depth 1 https://github.com/xsolla/xsolla-ai-kitWrote 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.
[](https://agentmods.dev/instructions/xsolla/xsolla-ai-kit/claude-md)<a href="https://agentmods.dev/instructions/xsolla/xsolla-ai-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/xsolla/xsolla-ai-kit/claude-md/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.
<a href="https://agentmods.dev/instructions/xsolla/xsolla-ai-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/xsolla/xsolla-ai-kit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01508 | $0.01508 |
| Opus 5.5 | $0.00603 | $0.00603 |
| Sonnet 5.5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
xsolla-ai-kit CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- No `curl` commands — skills describe intent, not raw HTTP This is a copy
100% identical to xsolla-ai-kit AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xsolla-ai-kit — Agent Context
This file is read automatically by most AI coding agents (Cursor, Codex CLI, GitHub Copilot, Windsurf, Amp, Devin, Jules, Aider, Roo Code, Augment). Claude Code users: CLAUDE.md is a copy of this file.
What this repo is
xsolla/xsolla-ai-kit is the Xsolla agent skills toolkit — a collection of SKILL.md files (agentskills.io format) that teach AI coding agents how to execute Xsolla-specific workflows end-to-end.
On the headless path, skills call Xsolla REST APIs directly. The Shop Builder path uses the Xsolla CLI 1.9.4 or later today (brew install xsolla/xsolla-cli/xsolla). A new Shop Builder store opens in the Editor and preview only when the CLI has shopbuilder create-block; nocode-shop-setup checks that before anything else.
Shop building paths
Two ways to build a shop, for different goals. Before building, find out whether the user is ready to code, review, test, and deploy, and whether they already have a store to plug into. Don't ask what is already clear. A user who says they will write the code goes to code. Otherwise, with no local repo, or when the user says they don't code, the path is Shop Builder: say so and continue. Ask only when a repo with storefront code exists and the user hasn't said.
In code — shop-setup. The agent writes the shop on the user's machine. The user deploys, tests, and reviews it. They control the logic and the styles: a store from scratch, or Xsolla products embedded in a store they already have. The usual payment UI is Headless Checkout, a component library. Pay Station, the hosted payment page, is the other option.
In Shop Builder — nocode-shop-setup. The agent sends commands to Shop Builder, and the site is created there. The user arranges blocks, configures them, and publishes. This fits someone who does not want to own the HTML, JavaScript, backend, deploys, or the upkeep of their own storefront. Custom blocks are possible; that code still runs on Xsolla's side. Payments use Pay Station. A store continues in description-to-shop or shop-builder-assembly. A PC game home around the store continues in game-web-portal.
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.
- 2d ago Changed · +97 tokens per session ff0cc083ac69
- 6d ago Changed · -1 lines · +75 tokens per session 806fbc59b392
- 15d ago Changed · +13 lines · +213 tokens per session 4881d4d8ea30
- 23d ago Changed · +8 tokens per session ebad833a9b86
- 29d ago Changed · +25 lines · +369 tokens per session 104dd6fda073
- 2mo ago First seen · 83 lines · 746 tokens per session scan A 2856d8114241
xsolla-ai-kit CLAUDE.md is an instructions file published in the GitHub repository xsolla/xsolla-ai-kit (9 stars, last pushed today), licensed MIT. It adds 1,508 tokens to every session, about $0.0060 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to xsolla-ai-kit AGENTS.md, differing in 0 lines, and is treated as a copy.
xsolla-ai-kit CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xsolla-ai-kit CLAUDE.mdxsolla/xsolla-ai-kit | Instructions file | 9 | today | MIT | A | 1,508 | Claude Code |
| vibetags com-example-service-OrderService.instructions.mdPIsberg/vibetags | Instructions file | 25 | yesterday | MIT | A | 553 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |