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/molcrafts/molmcp/claude-mdgit clone --depth 1 https://github.com/MolCrafts/molmcpWrote 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/molcrafts/molmcp/claude-md)<a href="https://agentmods.dev/instructions/molcrafts/molmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/molcrafts/molmcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01691 | $0.01691 |
| Opus 5 | $0.00846 | $0.00846 |
| Sonnet 5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
molmcp 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 4d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
What this repo is
molmcp is FastMCP-composed MCP for MolCrafts: molmcp serve starts the
molcrafts core (knowledge plus list_planes / route) and mounts enabled
providers with official namespaces (molvis_open). molmcp init <host>
installs the usage skill and one MCP entry. Science APIs are discovered
via the core and never mirrored as MCP tools. Pure Python (>= 3.12),
src/ layout, managed with uv.
Protocol: MCP 2026-07-28 via FastMCP 4.0.0b5 + MCP Python SDK
v2 (mcp>=2). Do not pin FastMCP back to 3.x without an explicit decision.
Where things live
- Source code:
src/molmcp/ - Tests:
tests/ - Public documentation:
docs/(zensical site; concepts / guides / reference) - Passive project knowledge (notes, decisions, blueprint):
.claude/notes/ - Active runtime specs (alive, deleted on completion):
.claude/specs/ - Claude Code runtime config:
.claude/settings.local.json
Default workflow
For non-trivial work, prefer:
- plan (
/mol:specor write to.claude/notes/) - implement (
/mol:implor/mol:fix) - review (
/mol:review) - capture decisions (
/mol:note)
Configuration
Settings live in ~/.molmcp/settings.json, with optional per-project
.molmcp/settings.json and .molmcp/settings.local.json layered over it,
edited via molmcp config get|set|add|remove (see src/molmcp/settings.py).
No environment variables. tests/test_no_env_switches.py fails the
build if a module reads one. Three exemptions are listed there with their
reason. Two are secrets — the bearer token an HTTP-transport server compares
against, and GITHUB_TOKEN for github: sources; the third builds a child
process environment and reads nothing. Each names a
variable in config rather than storing its value — a settings file that can
be committed is the wrong place for a credential. Configuration that lives only in one shell
cannot be reported by molmcp config list, and two plane servers launched
by different clients would silently disagree about it.
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.
- 4d ago First seen · 147 lines · 1,691 tokens per session scan A 3b09ed42e1f2
molmcp CLAUDE.md is an instructions file published in the GitHub repository MolCrafts/molmcp (0 stars, last pushed 7d ago), licensed BSD-3-Clause. It adds 1,691 tokens to every session, about $0.0085 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
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).
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.
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 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.