claude-viewer: Instructions file for Claude Code

CLAUDE.md

claude-viewer CLAUDE.md is an instructions file for Claude Code from maxturazzini/claude-viewer. It costs 1,061 tokens per session, scanned B, original, MIT.

A Claude Code instruction file for Claude Viewer, an admin tool that displays Claude Code conversation history, usage, models, and tool activity. It also documents the project's commands, data files, and technology choices.

In plain words
What is it for?
Setting up, running, and modifying Claude Viewer, including its web server, conversation data, analytics, and MCP integration.
Why use it?
It gives an AI assistant the project context and account-handling rules needed to work consistently in the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is maxturazzini/claude-viewer's own configuration. It tells Claude Code how to work on claude-viewer 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 claude-viewer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to maxturazzini/claude-viewer. 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/maxturazzini/claude-viewer/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/maxturazzini/claude-viewer

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 claude-viewer CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/maxturazzini/claude-viewer/claude-md"><img src="https://agentmods.dev/badge/instructions/maxturazzini/claude-viewer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,061 This file is loaded in full into every session.
When invoked 1,061 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01061 $0.01061
Opus 5.5 $0.00424 $0.00424
Sonnet 5.5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured 2mo ago against content hash 1ca3f91fad76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

claude-viewer CLAUDE.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

// ~/.claude/settings.json
CLAUDE.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 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 when working with this repository.

GitHub Account

Before any GitHub operations (push, PR, etc.), switch to the correct account:

gh auth switch -u maxturazzini

Project Overview

Claude Viewer is an admin tool that visualizes Claude Code conversation history from all users on a machine. It uses a dual-source data approach:

  1. Primary: ~/.claude/history.jsonl - Quick conversation list
  2. Enrichment: ~/.claude/projects/{project}/{session-uuid}.jsonl - Full conversation details

Key Features:

  • Full conversations (user prompts AND Claude responses)
  • Token usage analytics (input/output/cache)
  • Model tracking (sonnet-4-5, opus, haiku)
  • Tool usage analytics (WebSearch, Bash, Edit, etc.)
  • MCP Server for Claude Desktop/Code integration

Tech Stack

  • Backend: Node.js + Express.js (v4.18.2)
  • MCP Server: Model Context Protocol with stdio transport
  • Frontend: Vanilla JavaScript, HTML5, CSS3
  • Data: JSONL files from Claude Code history
  • Platform: Cross-platform (macOS, Linux, Windows)

Development Commands

# Install dependencies
npm install

# Start web server
npm start

# Run MCP server
npm run mcp

# Default port: 2204 (configurable via CLAUDE_VIEWER_PORT env)

MCP Server

Tools Available

Tool Description Parameters
get_claude_users List users with Claude history -
get_conversations Get conversations with filters username?, search?, project?, dateFrom?, dateTo?, limit?, offset?
get_stats Aggregated usage statistics -
get_conversation_details Full transcript of a session sessionId, username
open_dashboard Start server and open browser port? (default: 2204)

Configuration

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "claude-viewer": {
      "command": "node",
      "args": ["/path/to/claude-viewer/mcp-server.js"]
    }
  }
}

Read the full file on GitHub · 143 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. 2mo ago First seen · 143 lines · 1,061 tokens per session scan B 1ca3f91fad76

Subscribe to this mod's changes

claude-viewer CLAUDE.md is an instructions file published in the GitHub repository maxturazzini/claude-viewer (0 stars, last pushed 8mo ago), licensed MIT. It adds 1,061 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

claude-viewer CLAUDE.md compared with instructions from other repositories

claude-viewer CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-viewer CLAUDE.mdmaxturazzini/claude-viewerInstructions file08mo agoMITB1,061Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode