live-ketcher-mcp: Instructions file for Codex

AGENTS.md

live-ketcher-mcp AGENTS.md is an instructions file for Codex, OpenCode from MALeitch/live-ketcher-mcp. It costs 3,063 tokens per session, scanned A, original, MIT.

Project-specific development instructions for live-ketcher-mcp, an MCP server that connects an agent to the Ketcher chemical structure editor.

In plain words
What is it for?
Use it when modifying the Ketcher connector, transport, bridge, domain logic, or MCP tools, especially when working with visible browser sessions and whole-document updates.
Why use it?
It records architecture, rules, and required checks so changes do not accidentally replace only part of a chemical document or break the live browser connection.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is MALeitch/live-ketcher-mcp's own configuration. It tells Codex and OpenCode how to work on live-ketcher-mcp 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 live-ketcher-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MALeitch/live-ketcher-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.

Copy the file
curl -O https://raw.githubusercontent.com/MALeitch/live-ketcher-mcp/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/MALeitch/live-ketcher-mcp

Made for: Codex, OpenCode.

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 live-ketcher-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maleitch/live-ketcher-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/maleitch/live-ketcher-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/maleitch/live-ketcher-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/maleitch/live-ketcher-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.

agentmods 80×15 button for live-ketcher-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/maleitch/live-ketcher-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/maleitch/live-ketcher-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,063 This file is loaded in full into every session.
When invoked 3,063 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 $0.03063 $0.03063
Opus 5 $0.01532 $0.01532
Sonnet 5 $0.00613 $0.00613
Haiku 4.5 $0.00306 $0.00306

Measured 10d ago against content hash d42810f1ad60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

live-ketcher-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 10d 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.

AGENTS.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development notes

Read this before changing ketcher_connector/. ROADMAP.md carries the full port scope and the prototype measurements behind these rules.

Architecture

ketcher_connector/
  transport/
    connection.py  launch/attach a live, visible browser running Ketcher
    document.py    read_document/apply_transform -- the whole-document rule
    identity.py    stable claude-* ids via content hash, no native tags
    internals.py   quarantined below-API access (undo/redo/selection)
    worker.py      dedicated thread owning the Playwright session --
                   NOT optional, see rule 4 below
  domain/      pure logic, zero editor imports, pytest-covered
  bridge/      the seam: every tool call goes through here, async
tools/         thin MCP tool definitions, async where they touch the bridge

All four Phase 0 transport modules and the bridge/server skeleton are written and verified live (both via direct script and via a real mcp.call_tool round trip) as of this note. test_smoke_visual.py exercises all of it.

Non-negotiable rules

1. Read the whole document, write the whole document

ketcher.setMolecule() replaces the entire canvas. Measured on a 3-molecule canvas: writing back only the first molecule took it from 13 atoms to 6 and silently destroyed the user's other two structures.

The transport must expose a read_document() / write_document() pair that makes a partial write structurally impossible from the tool layer. Never call setMolecule with a subset of root.nodes.

Recoverable via undo if it does happen, but do not rely on that.

2. Do not reach below window.ketcher.* without quarantining it

The documented API surface is the Ketcher class in ketcher-core/src/application/ketcher.ts. Everything else (editor.selection(), editor.historyStack, editor.historyPtr, editor.struct(), drawingEntitiesManager) works but is unversioned and can break across Ketcher releases.

Confine all of it to one module in transport/ so a Ketcher upgrade has a single blast radius. editor.undo()/redo()/historySize() are needed for the undo tools and are the main reason this exception exists at all.

Read the full file on GitHub · 244 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. 10d ago First seen · 244 lines · 3,063 tokens per session scan A d42810f1ad60

Subscribe to this mod's changes

live-ketcher-mcp AGENTS.md is an instructions file published in the GitHub repository MALeitch/live-ketcher-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 3,063 tokens to every session, about $0.0153 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 · 5,153 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

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

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