cdxml-toolkit-community: Instructions file for Claude Code

CLAUDE.md

cdxml-toolkit-community CLAUDE.md is an instructions file for Claude Code from ZiChenWang114514/cdxml-toolkit-community. It costs 3,910 tokens per session, scanned A, original, MIT.

A set of instructions for using cdxml-toolkit, a chemistry office-automation toolkit that works with ChemDraw files and laboratory data. It tells coding agents how to use its MCP tools and handle chemical structures safely.

In plain words
What is it for?
Drawing molecules and reaction schemes, parsing electronic lab-notebook exports, analysing LCMS and NMR data, completing lab books, and working with ChemDraw files in PowerPoint or Word.
Why use it?
It gives the agent project-specific rules for drawing molecules, processing lab data, and editing ChemDraw documents without inventing chemical structures or exposing file contents.

Instructions file for Claude Code

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

This is ZiChenWang114514/cdxml-toolkit-community's own configuration. It tells Claude Code how to work on cdxml-toolkit-community 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 cdxml-toolkit-community configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ZiChenWang114514/cdxml-toolkit-community. 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/ZiChenWang114514/cdxml-toolkit-community/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ZiChenWang114514/cdxml-toolkit-community

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 cdxml-toolkit-community CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zichenwang114514/cdxml-toolkit-community/claude-md.svg)](https://agentmods.dev/instructions/zichenwang114514/cdxml-toolkit-community/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zichenwang114514/cdxml-toolkit-community/claude-md"><img src="https://agentmods.dev/badge/instructions/zichenwang114514/cdxml-toolkit-community/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,910 This file is loaded in full into every session.
When invoked 3,910 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 $0.03910 $0.03910
Opus 5 $0.01955 $0.01955
Sonnet 5 $0.00782 $0.00782
Haiku 4.5 $0.00391 $0.00391

Measured 6d ago against content hash 1fb20a33f81b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cdxml-toolkit-community 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 6d 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 · 412 lines

How it starts

The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cdxml-toolkit — Agent Reference

What this is

A chemistry office automation toolkit with 15 compatible core MCP tools and a 35-tool community profile. Agents use these tools to draw molecules, render reaction schemes, parse ELN exports, analyze LCMS/NMR data, complete lab books, and manipulate ChemDraw files in PowerPoint/Word.

All structure output is CDXML (ChemDraw XML). Uses ACS Document 1996 style.

Key rules

  1. Ground every molecule. Connectivity may come from a trusted value supplied by the user or from resolve_name, modify_molecule, parse_reaction, or an OCSR tool. Never invent a SMILES from model knowledge or visual inspection.
  2. Verify structural edits. Route intentional changes through modify_molecule; inspect its MCS diff before drawing. A trusted SMILES that requires no modification can be passed to draw_molecule.
  3. Never return large output inline. Tools write files and return {ok, output_path, size}. Use summarize_reaction to view parse_reaction output — do not read the full JSON.
  4. CDXML is the interchange format. Binary CDX files must be converted via convert_cdx_cdxml.

MCP server

python -m cdxml_toolkit.mcp_runtime                              # stdio
python -m cdxml_toolkit.mcp_runtime --profile office             # smaller profile
python -m cdxml_toolkit.mcp_runtime --transport streamable-http  # network service

Tool reference

Read docs/mcp-tools.md for all generated signatures. The sections below describe the compatible core tools.

resolve_name

Resolve any chemical identifier to a rich molecule descriptor.

resolve_name(query="aspirin")
resolve_name(query="Cs2CO3")
resolve_name(query="534-17-8")       # CAS number
resolve_name(query="CF3")            # fragment → prefix form

Returns: {ok, name, smiles, formula, mw, exact_mass, iupac_name, source, role, display_text, prefix_form}

5-tier chain: curated reagent DB (186 entries) → condensed formula parser → ChemScript IUPAC (preferred) → OPSIN (bundled offline fallback) → PubChem.

Read the full file on GitHub · 412 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. 6d ago First seen · 412 lines · 3,910 tokens per session scan A 1fb20a33f81b

Subscribe to this mod's changes

cdxml-toolkit-community CLAUDE.md is an instructions file published in the GitHub repository ZiChenWang114514/cdxml-toolkit-community (1 stars, last pushed 12d ago), licensed MIT. It adds 3,910 tokens to every session, about $0.0196 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 · 5,182 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

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

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