Borrowing it
Nothing to install: this file belongs to jurimaxam-dotcom/chemdraw-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.
curl -O https://raw.githubusercontent.com/jurimaxam-dotcom/chemdraw-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jurimaxam-dotcom/chemdraw-mcpWrote 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/jurimaxam-dotcom/chemdraw-mcp/claude-md)<a href="https://agentmods.dev/instructions/jurimaxam-dotcom/chemdraw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jurimaxam-dotcom/chemdraw-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.
<a href="https://agentmods.dev/instructions/jurimaxam-dotcom/chemdraw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jurimaxam-dotcom/chemdraw-mcp/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 | $0.03342 | $0.03342 |
| Opus 5 | $0.01671 | $0.01671 |
| Sonnet 5 | $0.00668 | $0.00668 |
| Haiku 4.5 | $0.00334 | $0.00334 |
Grade A, and why
chemdraw-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.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chemdraw-mcp
MCP server for Claude Desktop that turns molecule names or SMILES into publication-style 2D structure drawings. PNG/SVG are the primary outputs (rendered offline via RDKit) — ChemDraw CDXML is an optional extra format, never a runtime requirement.
Build / Run
./install.sh # one-command setup: uv + deps + Claude Desktop config
uv sync # deps only
uv run chemdraw-tool-server # run the MCP server (stdio) manually
uv run chemdraw-doctor # diagnose the installation (env, paths, network)
install.sh registers the server via chemdraw_tool/desktop_config.py
(idempotent merge, writes a .bak backup, never touches other configured MCP
servers). The config logic lives in the package, not in scripts/, because the
wheel ships only chemdraw_tool — PyPI users get chemdraw-install and a fully
working chemdraw-doctor from it. Claude Desktop launches MCP servers with a
minimal GUI PATH, so command must be an absolute path; the installer resolves
it and prints what it wrote.
If a host keeps the server process alive (Claude Desktop does), restart it
after changing server code or dependencies — a stale process mixes old
in-memory modules with new files and manifests as confusing RDKit/Boost
signature errors. Restart it yourself after such changes (osascript -e 'quit app "Claude"' && sleep 2 && open -a Claude); an MCP stdio handshake
(initialize → tools/list) is the hard proof that the registered command works.
Auto-Gate (the project's green/red)
./test.sh # lint + backend + bundle + frontend
npm --prefix chemdraw_tool/ui run test:watch # JS unit tests in watch mode
./scripts/handshake.sh # real stdio handshake (needs network)
One-time frontend setup: cd chemdraw_tool/ui && npm install && npx playwright install chromium
handshake.sh sits outside the gate because its first run downloads the MCP
Inspector. It is the only check that starts the server the way Claude Desktop
does — the absolute command out of claude_desktop_config.json — and asserts
the two numbers the Python side predicts (currently 20 tools, 14 with a panel).
In-process tests cannot see the two failure modes that have actually cost time
here: a stale server process and a GUI PATH that cannot find uv.
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.
- 9d ago First seen · 245 lines · 3,342 tokens per session scan A 30e5e2c8b856
chemdraw-mcp CLAUDE.md is an instructions file published in the GitHub repository jurimaxam-dotcom/chemdraw-mcp (13 stars, last pushed 25d ago), licensed Apache-2.0. It adds 3,342 tokens to every session, about $0.0167 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.
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).
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.
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.