Borrowing it
Nothing to install: this file belongs to muthanii/waylMCP. 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/muthanii/waylMCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/muthanii/waylMCPWrote 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/muthanii/waylmcp/claude-md)<a href="https://agentmods.dev/instructions/muthanii/waylmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/muthanii/waylmcp/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/muthanii/waylmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/muthanii/waylmcp/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 | $0.02775 | $0.02775 |
| Opus 5 | $0.01388 | $0.01388 |
| Sonnet 5 | $0.00555 | $0.00555 |
| Haiku 4.5 | $0.00278 | $0.00278 |
Grade A, and why
waylMCP 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for working in this repository.
What this is
An MCP server that exposes the Wayl payments API as tools. Wayl is an Iraqi payment gateway: you create a payment link, send its URL to the buyer, and they pay on Wayl's hosted checkout. The server is domain-neutral — goods, digital downloads, services and invoices all go through the same payment-link flow.
Python 3.10+, uv for dependency management, the official mcp SDK, stdio transport.
Layout
| Path | Purpose |
|---|---|
src/wayl_mcp/server.py |
All MCP tools. The only file that touches the MCP SDK. |
src/wayl_mcp/client.py |
httpx wrapper: auth header, response envelope, error mapping, retries. |
src/wayl_mcp/validation.py |
Client-side enforcement of Wayl's documented rules. Pure functions, no I/O. |
src/wayl_mcp/webhooks.py |
HMAC-SHA256 signature verification. Pure functions, no I/O. |
src/wayl_mcp/config.py |
Environment-variable config and the API's magic constants. |
docs/openapi.v1.json |
Vendored copy of Wayl's OpenAPI spec, fetched from https://api.thewayl.com/openapi.v1.json. |
tests/ |
pytest + respx. No test may touch the network. |
Commands
uv run pytest
uv run ruff check src tests
uv run wayl-mcp
Conventions
- Keep I/O out of
validation.pyandwebhooks.py. They are pure and directly unit-testable; that is why the rule checks live there and not inline in the tools. - Tool parameters are
snake_case; the Wayl API iscamelCase.server.pyis where the two meet — build the request body with the API's spelling. - Every tool needs a docstring. It becomes the tool description the model reads, and it is the main thing determining whether the tool gets used correctly. Say what the tool does, when to reach for it, and what the caller must be careful about.
- Use
Annotated[T, Field(description=...)]for every parameter. These become the JSON Schema descriptions. Constraints likege=1000are worth adding even thoughvalidation.pyalso checks them: the schema helps the model self-correct, and the Python check produces the better error message when something bypasses the schema. - Raise
ToolErrorfor anything the caller should see._callconvertsWaylErrorand the@_validateddecorator convertsValidationFailed. - Set
annotations=on new tools —READ_ONLY,WRITES,DESTRUCTIVE, orLOCAL_ONLY. Clients usedestructiveHintto decide whether to confirm with the user, which is the difference between a refund happening silently and not. - Always wrap interpolated path values in
path_segment(). Reference IDs and product IDs are free text, and an unescaped#truncates the URL —order#42becomes a request fororder, silently returning a different order's payment status. Same for?and/. It also encodes dots-only segments, because httpx resolves.and..as path navigation and an ID of.turns a single-order lookup into a request for the whole collection. - Put every constraint in the JSON Schema, not only in prose. Use
Literal[...]for closed sets andmin_length/max_length/gefor bounds. A constraint the model can see costs nothing; one it discovers by failing costs a turn.validation.pystill checks the same rules for callers that bypass the schema.
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.
- 8d ago First seen · 188 lines · 2,775 tokens per session scan A 9aaae4a4cda7
waylMCP CLAUDE.md is an instructions file published in the GitHub repository muthanii/waylMCP (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,775 tokens to every session, about $0.0139 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.