Borrowing it
Nothing to install: this file belongs to MALeitch/live-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/MALeitch/live-chemdraw-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/MALeitch/live-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/maleitch/live-chemdraw-mcp/agents-md)<a href="https://agentmods.dev/instructions/maleitch/live-chemdraw-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/maleitch/live-chemdraw-mcp/agents-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/maleitch/live-chemdraw-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/maleitch/live-chemdraw-mcp/agents-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 | $0.09418 | $0.09418 |
| Opus 5 | $0.04709 | $0.04709 |
| Sonnet 5 | $0.01884 | $0.01884 |
| Haiku 4.5 | $0.00942 | $0.00942 |
Grade A, and why
live-chemdraw-mcp AGENTS.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 — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — live-chemdraw-mcp development notes
This file is for anyone reading the source in chemdraw_connector/ --
AI coding assistants and human contributors alike, whether you're
extending it, debugging something, or just want to understand why it's
built the way it is. Not for end users of the MCP server (see
README.md for that): none of this matters if you're only talking to
the server through Claude, since it exists precisely to hide these
details from that caller. It covers the package layout and, more
importantly, the ChemDraw COM quirks this connector was built around:
most of these were only found by driving live ChemDraw and watching it
misbehave, and re-deriving them from scratch is expensive. Read this
before working in chemdraw_connector/ for any reason.
Architecture
chemdraw_connector/
com/ COM plumbing only: worker (single STA thread, timeouts,
wedge detection), connection (attach/relaunch/reconnect),
types (COM enums <-> readable vocabulary)
domain/ pure logic, zero COM imports, pytest-covered
bridge/ the seam: every tool call goes through here
__init__.py composes ChemDrawBridge from the mixins below
_annotations.py, _document_session.py, _enumeration.py, _layout.py,
_manipulation.py, _plumbing.py, _properties_qc.py, _reaction.py,
_selection.py, _shorthand.py, _specialty_objects.py, _state_diff.py,
_stereochemistry.py, _structure_io.py,
_style.py one focused mixin per concern (document lifecycle,
layout, shorthand contraction, stereochemistry...)
targets.py structure addressing (tags, selection, doc) + safe
doc-scoped atom/bond access
state.py canvas snapshots for get_document_state / diff
snapshots.py automatic .cdxml backups before batch operations
tools/ thin MCP tool definitions
server.py FastMCP entry point (stdio)
docs/com_typelib/ — a live COM reflection dump of ChemDraw's full type
library (interfaces/methods/enums), plus the reusable probe scripts that
generated it. This is the source of truth for COM surface confirmed to exist
but not yet implemented in this connector (native stoichiometry grids,
Markush/alt-groups, as of the 2026-07-21 capture — mechanism/reaction arrow
types, atom isotope labeling, reaction symbols, enhanced-stereo flags,
polymer brackets, and TLC plates are now implemented, see README.md's
Capabilities section) — see its own README for details.
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 · 559 lines · 9,418 tokens per session scan A 8a6ef475b39a
live-chemdraw-mcp AGENTS.md is an instructions file published in the GitHub repository MALeitch/live-chemdraw-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 9,418 tokens to every session, about $0.0471 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.