Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/atomflow-ai/molecode/agents-mdgit clone --depth 1 https://github.com/AtomFlow-AI/MoleCodeWhat 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 | $0.00847 | $0.00847 |
| Opus 5 | $0.00424 | $0.00424 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
MoleCode 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — MoleCode
Guidance for coding agents (Claude Code, Codex, and compatible tools) working in this repository.
What this repo is
MoleCode is an LLM-native molecular representation: it serializes a molecule
as an explicit Mermaid graph where every atom and bond
is a typed, named node/edge, losslessly inter-convertible with SMILES / MOL via
RDKit. It covers three domains with one grammar — small molecules, polymers
(PSMILES repeat units), and Markush structures ({} R-groups).
The installable library lives in molecode/; user-facing docs are
in docs/; runnable examples in examples/.
Use the MoleCode skill
A ready-to-use Agent Skill ships in this repo at
.claude/skills/molecode/:
- Claude Code auto-discovers it (standard
.claude/skills/location). Just ask about understanding or editing a molecule and themolecodeskill applies. - Codex / other agents: read
.claude/skills/molecode/SKILL.mdand use the bundled CLI below. Interface metadata is in.claude/skills/molecode/agents/openai.yaml.
MoleCode-first rule
For any molecule understanding or editing task, work at the explicit graph level: convert SMILES → MoleCode, inspect/edit the named nodes and edges, then validate and convert back. This is more reliable than reasoning over linear SMILES and safer than hand-writing a new SMILES for structural edits.
CLI quick start
# from the repo root (the script finds the molecode package automatically)
python .claude/skills/molecode/scripts/molecode_convert.py doctor
python .claude/skills/molecode/scripts/molecode_convert.py smiles-to-molecode "CCO" --name Ethanol
python .claude/skills/molecode/scripts/molecode_convert.py validate --input edited.mmd
python .claude/skills/molecode/scripts/molecode_convert.py molecode-to-smiles --input edited.mmd
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.
- yesterday First seen · 70 lines · 847 tokens per session scan A c3ea17bbaa0b
MoleCode AGENTS.md is an instructions file published in the GitHub repository AtomFlow-AI/MoleCode (297 stars, last pushed 2mo ago), licensed MIT. It adds 847 tokens to every session, about $0.0042 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 2026-08-30.
Other instructions, from other repositories
wisp-science AGENTS.md
AGENTS.md instructions for xuzhougeng/wisp-science, covering agents.md, project orientation, repository layout, engineering rules and verification commands.
open-science AGENTS.md
AGENTS.md instructions for ai4s-research/open-science, covering open science desktop, design principles, what this project is, repository map and architecture guardrails.
open-science CLAUDE.md
Claude Code instructions for ai4s-research/open-science, a project described as: Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.
ai4science-studio CLAUDE.md
Instructions for AMDResearch/ai4science-studio, covering claude.md, repository purpose, agent entry points (read these first), directory layout and model slug rule.
terminal-bench-science CLAUDE.md
Instructions for harbor-framework/terminal-bench-science, a project described as: Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains.
statlingo AGENTS.md
AGENTS.md instructions for bgreenwell/statlingo, covering agents.md for statlingo, 1. project overview & mission, 2. repository layout, 3. the canonical prompts system (prompts/) and prompt synchronization.