Borrowing it
Nothing to install: this file belongs to talirezun/MV-MCP-server. 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/talirezun/MV-MCP-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/talirezun/MV-MCP-serverWrote 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/talirezun/mv-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/talirezun/mv-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/talirezun/mv-mcp-server/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/talirezun/mv-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/talirezun/mv-mcp-server/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 | $0.00966 | $0.00966 |
| Opus 5.5 | $0.00386 | $0.00386 |
| Sonnet 5.5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
MV-MCP-server 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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MV Travel MCP Server
MCP server giving AI assistants access to the MV Travel (formerly MountVacation) accommodation API. It is in production with real users — treat every change as a production change.
Working state
This repository's working state lives in The Curator (project projects/mv-travel-mcp, see
.curator-project). At the START of every session call the my-curator MCP tool
get_project_context with project "mv-travel-mcp" and read the standing brief and latest
handoff before acting. When the user says continue or resume, or you come back after a
pause, call get_project_context again before acting — another tool or computer may have
saved since. SAVE with save_working_state under project "mv-travel-mcp" with the
scope argument set to your tool's name — "claude-code" if you are Claude Code,
"antigravity" if you are Antigravity, "opencode" if you are opencode, otherwise your
tool's own name, lowercase and hyphenated. Pass scope explicitly every time, and never
save under another tool's scope. Save after every material
decision, at least every ten tool calls, and ALWAYS before you stop; a save overwrites,
so send the complete state each time. Pass harness as that same name and model as
your exact model id if you know it (omit it otherwise — never search files for it), and
record the seen map as foundations_read.
This project also keeps foundations — canonical documents such as its architecture and firm
decisions — that travel with it. get_project_context is the call that returns them with
the brief and handoff, so make it your first action of the session, before you read code
or run anything. Its seen map holds their hashes: passing that back as foundations_read
on every save is how the next session learns which of them changed.
Some foundations may be skeletons — prompts, not facts; the document says so
at the top. As you learn the project, fill each one and save it with
save_foundation (commissioned_by_owner: true — this block is the owner's
commission). If the project has a repository, export the filled
foundations into its docs/ folder on the first commit.
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.
- 9d ago First seen · 52 lines · 966 tokens per session scan A db2ba4beb348
MV-MCP-server CLAUDE.md is an instructions file published in the GitHub repository talirezun/MV-MCP-server (2 stars, last pushed 9d ago), licensed MIT. It adds 966 tokens to every session, about $0.0039 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 2026-10-28.
MV-MCP-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| MV-MCP-server CLAUDE.mdtalirezun/MV-MCP-server | Instructions file | 2 | 9d ago | MIT | A | 966 | Claude Code |
| 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 |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |