Borrowing it
Nothing to install: this file belongs to agarwalvishal/claude-chat-exporter. 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/agarwalvishal/claude-chat-exporter/main/CLAUDE.mdgit clone --depth 1 https://github.com/agarwalvishal/claude-chat-exporterWrote 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/agarwalvishal/claude-chat-exporter/claude-md)<a href="https://agentmods.dev/instructions/agarwalvishal/claude-chat-exporter/claude-md"><img src="https://agentmods.dev/badge/instructions/agarwalvishal/claude-chat-exporter/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/agarwalvishal/claude-chat-exporter/claude-md"><img src="https://agentmods.dev/badge/instructions/agarwalvishal/claude-chat-exporter/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 | $0.04770 | $0.04770 |
| Opus 5 | $0.02385 | $0.02385 |
| Sonnet 5 | $0.00954 | $0.00954 |
| Haiku 4.5 | $0.00477 | $0.00477 |
Grade A, and why
claude-chat-exporter CLAUDE.md scanned grade A 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **The core script is embedded verbatim at install time.** `fetch(RAW)` runs on the *install page*; the result is baked into the `javascript:` URL. The bookmarklet never fetches code at runtime, so **merging to `main` d How it starts
The opening of the file, as written. The whole thing — 197 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.
What this is
A single-file browser-console script (claude-chat-exporter.js) that exports a claude.ai conversation to a markdown file. It runs by pasting the whole file into the browser devtools console while a conversation is open (a one-click bookmarklet in docs/index.html wraps the same script). There is no build system, package manager, test suite, or lint config — the whole repo is the script, README.md, docs/index.html, this file, LICENSE, .github/FUNDING.yml, and .claude/skills/ — none of which any code reads.
To test a change: node --check claude-chat-exporter.js for syntax, then paste the edited script into the console on a real claude.ai conversation and observe the on-page status indicator and downloaded .md file.
main is the release channel. No tags, no releases, no build artifact: the install page fetches claude-chat-exporter.js straight from main, and the update check compares against main. GitHub Pages serves docs/ from main. Merging to main is publishing — every script change immediately becomes what new installs get and flips existing bookmarklets to "update available". The script's hash is the version signal; there is no version number anywhere.
Core design decision
The script reads nothing from Claude's rendered page. It takes the conversation directly from claude.ai's own internal API, whose response already contains each message's source markdown (tables, math, code, etc.) — so fidelity is byte-perfect with zero conversion logic. Reject any change that reads the conversation from the page — DOM scraping, driving Claude's own buttons, intercepting the clipboard, or parsing HTML into markdown. All of it works against the point of the project.
The script contains zero CSS selectors — no querySelector, no aria-label matching, no class names — which is what makes Claude's markup and its localisation unable to break it. It does legitimately touch the DOM, so don't "fix" that: document.createElement and document.body for the download link and the status box (plus its sponsor link), window focus/blur listeners plus a housekeeping interval, a window.__claudeChatExporterDispose marker so a repeat click replaces the box instead of stacking another, a read of window.__claudeChatExporterNotice (published by the install page's update notice while it is on screen) so the box keeps clear of it, document.cookie for lastActiveOrg, window.location for the conversation id. Reading Claude's markup is the prohibited part, not touching the DOM at all.
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.
- today Changed · +1 lines · +227 tokens per session 9143899c289f
- 11d ago First seen · 196 lines · 4,543 tokens per session scan A 276e03b76360
claude-chat-exporter CLAUDE.md is an instructions file published in the GitHub repository agarwalvishal/claude-chat-exporter (676 stars, last pushed yesterday), licensed MIT. It adds 4,770 tokens to every session, about $0.0238 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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.
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).
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.
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).
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.