Borrowing it
Nothing to install: this file belongs to ilyannn/wallos-mcp. 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/ilyannn/wallos-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/ilyannn/wallos-mcpWrote 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/ilyannn/wallos-mcp/claude-md)<a href="https://agentmods.dev/instructions/ilyannn/wallos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ilyannn/wallos-mcp/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/ilyannn/wallos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ilyannn/wallos-mcp/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 | $0.01912 | $0.01912 |
| Opus 5.5 | $0.00765 | $0.00765 |
| Sonnet 5.5 | $0.00382 | $0.00382 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
wallos-mcp 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 2mo 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with the Wallos MCP server codebase.
Project Overview
Wallos MCP Server is a Model Context Protocol server that enables Claude Desktop to interact with Wallos subscription management instances. This TypeScript project uses Bun runtime and provides comprehensive tooling for development and deployment.
Development Commands
Use the just command runner for all development tasks:
Core Development
just setup- Initial project setup (install deps, create .env)just start- Start development server with auto-reloadjust dev- Alias for startjust build- Build TypeScript to JavaScriptjust test- Run test suitejust check- Run all quality checks (typecheck, lint, test)
Code Quality
just lint- Comprehensive linting (ESLint + TypeScript + Markdown)just fmt- Format code (Prettier + markdownlint)just typecheck- TypeScript type checking without buildingjust superlint- Fast Super Linter with project-relevant checksjust superlint-verbose- Comprehensive Super Linter with debug output
Docker Operations
just docker-build- Build Docker imagejust docker-run- Run MCP server in Dockerjust docker- Combined build and run
Testing & Debugging
just test-tool TOOL- Test specific MCP tooljust debug- Start with debug loggingjust smoke-test- Quick build verification
Utilities
just clean- Remove build artifactsjust rebuild- Full clean, install, build cyclejust update-deps- Update and audit dependenciesjust stats- Show project statistics
Architecture
Tech Stack
- Runtime: Bun (fast JavaScript runtime)
- Language: TypeScript
- Framework: Model Context Protocol SDK
- HTTP Client: axios with tough-cookie for session management
- Testing: Bun test framework
- Linting: ESLint + Prettier + markdownlint
- CI/CD: GitHub Actions with multi-platform Docker builds
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.
- 2mo ago First seen · 235 lines · 1,912 tokens per session scan A 12abcc653285
wallos-mcp CLAUDE.md is an instructions file published in the GitHub repository ilyannn/wallos-mcp (9 stars, last pushed 1y ago), licensed MIT. It adds 1,912 tokens to every session, about $0.0076 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 2026-08-31.
wallos-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wallos-mcp CLAUDE.mdilyannn/wallos-mcp | Instructions file | 9 | 1y ago | MIT | A | 1,912 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 279k | today | MIT | A | 4,325 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |