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/ching-chiang/comsol-mcp/claude-mdgit clone --depth 1 https://github.com/Ching-Chiang/comsol-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/ching-chiang/comsol-mcp/claude-md)<a href="https://agentmods.dev/instructions/ching-chiang/comsol-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ching-chiang/comsol-mcp/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 | $0.01127 | $0.01127 |
| Opus 5 | $0.00563 | $0.00563 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
comsol-mcp 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 5d 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.
This is a copy
95% identical to comsol-mcp AGENTS.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — comsol-server-mcp
Project Overview
COMSOL MCP Server (comsol-mcp v0.1.9). An attach-first MCP bridge that connects to a running COMSOL Multiphysics Server, loads a main .mph model, locks it, and drives the same server-side model that a COMSOL Desktop client visualizes in real time.
Architecture
comsol_mcp/
__init__.py # from .mcp_server import main
_server.py # FastMCP instance, global state, constants, classification sets
_state.py # Workflow persistence, status/operations logging, path/port utils, _run_tool
_connection.py # Disconnect, client shell, _require_client
_model.py # Model adopt/prune, visible-main lock mechanism
_model_ops.py # Pure helpers: parameters, expressions, core metrics, tree, geometry
_tools_connection.py # server_info, check_server_port, server_start, server_connect, server_disconnect
_tools_workflow.py # Workflow tools, visible-main lifecycle, model_tree, run_study
_tools_model.py # model_create, model_load, prune_loaded_models
_tools_params.py # get_parameters, set_parameters, evaluate_expressions, get_core_metrics
_tools_geometry.py # ensure_component/geometry/mesh, create/update/delete/run_feature
_tools_snapshot.py # run_visible_main_iteration, save_main_model_snapshot, commit_current_main_model, save_model
mcp_server.py # Thin entrypoint: imports + register + main()
35 MCP tools registered via mcp.add_tool() in each module's register() function.
Build and Run
pip install -e . # install in editable mode
pip install -e ".[dev]" # with pytest
python -m comsol_mcp.mcp_server # start MCP server
pytest # run tests (40 tests, all without COMSOL)
Module Dependency Graph
_server.py (no deps)
-> _state.py
-> _connection.py
-> _model.py
-> _model_ops.py (no global state deps)
Tool modules depend on the above:
_tools_connection -> _server, _state, _connection, _model
_tools_workflow -> _server, _state, _model, _tools_connection (cross-module call)
_tools_model -> _server, _state, _model
_tools_params -> _state, _model, _model_ops
_tools_geometry -> _state, _model, _model_ops
_tools_snapshot -> _server, _state, _model, _tools_params (cross-module call)
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.
- 5d ago First seen · 100 lines · 1,127 tokens per session scan A abb688b97cff
comsol-mcp CLAUDE.md is an instructions file published in the GitHub repository Ching-Chiang/comsol-mcp (11 stars, last pushed 3mo ago), licensed MIT. It adds 1,127 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to comsol-mcp AGENTS.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
bio-gene-to-reference-tree copilot-instructions.md
Copilot instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.
shannon-prover CLAUDE.md
Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.
torchcell CLAUDE.md
Claude Code instructions for Mjvolk3/torchcell, covering vision -- the virtual cell (north star), for local configs, git worktrees, programming guide and provenance & reproducibility.