agentmods.dev

lithium-vault-mcp: Instructions file for Claude Code

CLAUDE.md

lithium-vault-mcp CLAUDE.md is an instructions file for Claude Code from ciinkwia/lithium-vault-mcp. It costs 1,997 tokens per session, scanned A, original, MIT.

Instructions for using lithium-vault-mcp, a connector that lets Claude query paid primary-source data about lithium mining and battery metals. It explains its payment setup, price limit, tools, and testing.

In plain words
What is it for?
Maintaining, testing, republishing, or configuring the lithium-vault-mcp project and its wallet-based data access.
Why use it?
It documents how the connector pays for and accesses the research data, including the safety check that prevents requests above a chosen price.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: positional $N argument; mentions Claude Code.

This is ciinkwia/lithium-vault-mcp's own configuration. It tells Claude Code how to work on lithium-vault-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lithium-vault-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is set -a; source ../clink-wallet/.env; set +a.

not rated 0repo 1mo ago A scan 1,997 tokens original MIT
View source ↗ ciinkwia/lithium-vault-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to ciinkwia/lithium-vault-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.

Copy the file
curl -O https://raw.githubusercontent.com/ciinkwia/lithium-vault-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ciinkwia/lithium-vault-mcp

Made for: Claude Code.

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 lithium-vault-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ciinkwia/lithium-vault-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ciinkwia/lithium-vault-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ciinkwia/lithium-vault-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ciinkwia/lithium-vault-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.

agentmods 80×15 button for lithium-vault-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ciinkwia/lithium-vault-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ciinkwia/lithium-vault-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,997 This file is loaded in full into every session.
When invoked 1,997 The same file — it is already loaded in full.
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 $0.01997 $0.01997
Opus 5 $0.00999 $0.00999
Sonnet 5 $0.00399 $0.00399
Haiku 4.5 $0.00200 $0.00200

Measured 8d ago against content hash 508062db903f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lithium-vault-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 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.

CLAUDE.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lithium-vault-mcp

MCP server that exposes the Lithium Research Vault's three paid x402 tiers as MCP tools, so Claude Desktop / Claude Code users can query primary-source lithium mining data from inside their agent. Model A (bring-your-own-wallet): the server pays the vault's x402 fee from the caller's CDP wallet.

Lithium tie-in: this is the MCP distribution channel for the lithium-research vault (see ../clink-wallet/services/vault/). Part of the vault's go-to-market (../clink-wallet/services/vault/GO_TO_MARKET.md, item #6).

Scaffolded + PUBLISHED 2026-05-31.

  • npm: [email protected] (npx -y lithium-vault-mcp verified). Published by npm user baldwijw (ciinkwia's npm account, no 2FA) via a temporary granular bypass-2FA token — npm rejects a plain token with 403 even on no-2FA accounts. For republishes: npm login or a new bypass-2FA + read/write-all-packages granular token, then npm publish --access public.
  • GitHub: ciinkwia/lithium-vault-mcp (public).
  • End-to-end tested against Base mainnet (MCP→x402→vault→data) + price-guard verified.

Why Model A (and the seam to Model C)

Two models were weighed (see GO_TO_MARKET.md):

  • A — BYOW x402: caller pays from their own wallet; paywall intact; reaches only x402-equipped users. Chosen as a cheap experiment with bounded downside.
  • C — hosted freemium: free summary tier served direct from DuckDB, paid depth via x402; huge reach. The fallback if A stalls on adoption.

Decision (2026-05-31): ship A; switch to C if adoption stalls. A's likely failure mode (wallet friction) is itself the evidence that would justify C.

The code is structured so A→C is additive, not a rewrite:

  • src/tools.js — tool catalog (names, zod schemas, descriptions, tier). Transport- and payment-agnostic. Reused verbatim by C.
  • src/datasource.js — DataSource contract (fetchTier(tier, {entity, level})). A ships X402DataSource (pays the endpoint from the caller's wallet, with a pre-flight price-ceiling check). C adds a DirectDataSource (reads the vault DuckDB free + upsell) implementing the same contract.
  • src/x402.js — builds the x402-wrapped fetch bound to the caller's CDP wallet.
  • src/index.js — wires the MCP stdio transport + the chosen data source. C swaps stdio→HTTP and the data source here; tools.js untouched.

Read the full file on GitHub · 123 lines

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. 8d ago First seen · 123 lines · 1,997 tokens per session scan A 508062db903f

Subscribe to this mod's changes

lithium-vault-mcp CLAUDE.md is an instructions file published in the GitHub repository ciinkwia/lithium-vault-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,997 tokens to every session, about $0.0100 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.

Researchai-agentsclaudemcpmodel-context-protocolx402
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens