What is claude-threads CLAUDE.md?

Project instructions for Claude Threads, a lightweight web viewer for browsing Claude Code conversations stored as files. It describes the server, browser interface, styling, setup commands, and keyboard navigation.

Installing dependencies, starting the development server, and working on conversation browsing, search, panels, message rendering, or styling.

They give the coding agent the project structure and commands needed to change or run the viewer correctly.

How nibzard/claude-threads configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nibzard/claude-threads. 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/nibzard/claude-threads/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nibzard/claude-threads

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nibzard/claude-threads/claude-md/github.svg)](https://agentmods.dev/instructions/nibzard/claude-threads/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nibzard/claude-threads/claude-md"><img src="https://agentmods.dev/badge/instructions/nibzard/claude-threads/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nibzard/claude-threads/claude-md"><img src="https://agentmods.dev/badge/instructions/nibzard/claude-threads/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 974 This file is loaded in full into every session.

When invoked 974 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.

Model	Per session	Once invoked
Fable 5.1	$0.00974	$0.00974
Opus 5.5	$0.00390	$0.00390
Sonnet 5.5	$0.00195	$0.00195
Haiku 4.5	$0.00097	$0.00097

Measured 2mo ago against content hash 535ad8976888, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-threads 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.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 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 code in this repository.

Project Overview

This is a lightweight web viewer for Claude Code conversation files with a terminal-inspired ASCII aesthetic. It provides a file-system-based interface to browse projects from ~/.claude/projects and view JSONL conversation files in a compact, expandable format.

Development Commands

# Install dependencies
npm install

# Start development server (port 3000)
npm start
npm run dev

# No build process - uses vanilla HTML/CSS/JS

Architecture

Three-Tier Structure

Backend (server.js): Express server that scans ~/.claude/projects and serves JSONL files
Frontend (public/app.js): Single-page vanilla JavaScript application with vim-style keyboard navigation
Styling (public/style.css): GitHub Dark theme with terminal ASCII aesthetics

Key Components

ClaudeViewer Class (main frontend controller):

Project/conversation navigation with keyboard shortcuts (j/k/h/l)
Panel toggle system (sidebar/conversations can be hidden)
Message rendering with expandable tool calls and thinking blocks
Full-text search across all conversations

Server API Structure:

/api/projects - Returns projects with stats (total/assistant/user message counts)
/api/projects/:project/conversations - Lists conversations with metadata
/api/projects/:project/conversations/:file - Returns parsed JSONL messages
/api/search?q=term - Full-text search with result limiting

Data Flow

Server scans encoded project directories (-Users-path-project format)
Projects decoded to readable paths, URLs simplified to project names only
JSONL files parsed line-by-line for message objects
Frontend renders with expandable sections and syntax highlighting

Code Architecture

Message Rendering Pipeline

Content Types: text, thinking blocks, tool_use, tool_result
Rendering: Markdown-like processing with code block detection
Interactivity: Click-to-expand sections with yellow keyboard selection highlighting
Syntax Highlighting: Local implementation (replaced external CDN dependency)

Read the full file on GitHub · 117 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.

2mo ago First seen · 117 lines · 974 tokens per session scan A 535ad8976888

Subscribe to this mod's changes

claude-threads CLAUDE.md is an instructions file published in the GitHub repository nibzard/claude-threads (10 stars, last pushed 7mo ago), licensed MIT. It adds 974 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 2026-08-31.

claude-threads CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-threads CLAUDE.mdnibzard/claude-threads	Instructions file	10	7mo ago	MIT	A	974	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
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

claude-threads: Instructions file for Claude Code