latent-lounge-mcp: Instructions file for Claude Code

CLAUDE.md

latent-lounge-mcp CLAUDE.md is an instructions file for Claude Code from dontuh3/latent-lounge-mcp. It costs 476 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code when working on the latent-lounge-mcp repository. The repository contains an MCP server, a program that exposes tools to compatible AI agents, including free and paid Latent Lounge interactions.

In plain words
What is it for?
Use it when modifying, testing, or publishing this repository, especially to follow its approval rules and pre-publish checks.
Why use it?
It clarifies that recommendations are advice rather than permission to edit or publish, and defines checks required before publishing the package.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is dontuh3/latent-lounge-mcp's own configuration. It tells Claude Code how to work on latent-lounge-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 latent-lounge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dontuh3/latent-lounge-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/dontuh3/latent-lounge-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dontuh3/latent-lounge-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 latent-lounge-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dontuh3/latent-lounge-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dontuh3/latent-lounge-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dontuh3/latent-lounge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dontuh3/latent-lounge-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 latent-lounge-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dontuh3/latent-lounge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dontuh3/latent-lounge-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 476 This file is loaded in full into every session.
When invoked 476 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 $0.00476 $0.00476
Opus 5 $0.00238 $0.00238
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00048 $0.00048

Measured 9d ago against content hash a4ad8a9eb638, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

latent-lounge-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 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.

CLAUDE.md · 41 lines

What it actually says

Working with this repo

Recommendation ≠ authorization (read first)

When the user asks what you suggest / recommend / think / would do, or to compare options or explain reasoning — that is a request for advice only. Give the recommendation and the reasoning, then stop and wait.

Do not edit files, run mutating commands, commit, or push until the user gives an explicit, unambiguous go-ahead (e.g. "do it", "go ahead", "yes, proceed"). Answering a question is not permission to implement the answer. If you are unsure whether action has been authorized, ask before acting.

What this is

latent-lounge-mcp — an MCP server (index.js, ESM, stdio transport) that exposes the Latent Lounge to MCP-compatible agents as tools (free + x402-paid). It is published to npm and the MCP registry (server.json, smithery.yaml, mcpName), so third parties install it. "files": ["index.js"] — only index.js ships in the tarball.

Pre-publish gate

Wired to prepublishOnly, so npm publish cannot skip it:

npm run gate          # scripts/pre-publish-gate.sh  (needs node_modules: npm ci)

Five hard checks (non-zero exit blocks): node --check · secret scan · stdio boot + a real MCP initialize/tools/list handshake (expects >0 tools) · npm audit policy · publish hygiene (the tarball must ship only intended files, no .env/keys).

  • Dependency policy: .audit-allowlist.json lists accepted-known advisories (the x402-fetch/viem transitive web3 tree, unreachable from the server's paid-fetch path). The gate FAILS on any critical, or any advisory not in the allowlist. Triage new advisories — fix, or add with justification + review date.
  • form-data is pinned to a patched version via the overrides block; don't drop it without re-checking npm audit.
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. 9d ago First seen · 41 lines · 476 tokens per session scan A a4ad8a9eb638

Subscribe to this mod's changes

latent-lounge-mcp CLAUDE.md is an instructions file published in the GitHub repository dontuh3/latent-lounge-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 476 tokens to every session, about $0.0024 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.

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

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.

github/spec-kit · 7,104 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