multisim-mcp: Instructions file for Codex

AGENTS.md

multisim-mcp AGENTS.md is an instructions file for Codex, OpenCode from yxy050208/multisim-mcp. It costs 409 tokens per session, scanned A, original, MIT.

Repository instructions for developing the open-source Multisim MCP core, including compatibility, circuit simulation, hardware mapping, reports, and regression checks. MCP is a standard way for an AI tool to connect to external software.

In plain words
What is it for?
Use them when changing or reviewing the Multisim MCP codebase, especially work involving boards, circuits, simulation, or release compatibility.
Why use it?
They tell an agent which work belongs in the public project and which commercial-only features must not be added.

Instructions file for CodexOpenCode

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

This is yxy050208/multisim-mcp's own configuration. It tells Codex and OpenCode how to work on multisim-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 multisim-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yxy050208/multisim-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/yxy050208/multisim-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/yxy050208/multisim-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 multisim-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yxy050208/multisim-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/yxy050208/multisim-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yxy050208/multisim-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yxy050208/multisim-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 multisim-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yxy050208/multisim-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yxy050208/multisim-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 409 This file is loaded in full into every session.
When invoked 409 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 $0.00409 $0.00409
Opus 5.5 $0.00164 $0.00164
Sonnet 5.5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 10d ago against content hash f14397d2ee7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

multisim-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 · 34 lines

What it actually says

Open-source development scope

This checkout develops the public MIT-licensed Multisim MCP core.

  • Prioritize frontier engineering capabilities with reproducible evidence: complex circuits, component mapping, native verification, simulation, report export, protocol compatibility, and public release checks.
  • Basic multi-board integration remains an open-source development goal. Support explicit board assignments, connector/pin/fixture contracts, per-board native generation and simulation, cross-board interface validation, consolidated reports, and regression coverage. State supported versions and device families.
  • The commercial product prioritizes convenient installation, configuration, guided workflows, upgrades, and support in a separate private checkout. Keep existing public installation, CLI, and MCP connectivity compatible.
  • Future proprietary multi-board optimization, cross-board joint parameter or topology search, and advanced placement/wire-routing optimization belong to the commercial product. Do not implement, import, or publish those extensions here.
  • Support technical-leadership claims with measured public benchmarks and native evidence; do not claim universal superiority without a current comparison.
  • Preserve electrical-correctness fixes and compatibility of already public APIs. Basic pin connectivity and truthful validation remain core responsibilities.
  • Previously published multi-board and layout code retains its existing license; do not remove attribution, rewrite public history, or describe it as private.
  • Do not copy product bundles, customer data, private models, commercial prompts, evaluation sets, credentials, or deployment configuration from other checkouts. Shared folders and Git branches do not grant permission to publish their contents.
  • Review provenance before importing any patch from the commercial checkout. Ambiguous assets remain local until the owner identifies their public scope.
  • Stage exact reviewed files. Run python tools/release_audit.py --json before public delivery and verify built wheel/sdist with tools/check_mcp_package.py.

See the public scope policy and publishing guide.

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 · 34 lines · 409 tokens per session scan A f14397d2ee7b

Subscribe to this mod's changes

multisim-mcp AGENTS.md is an instructions file published in the GitHub repository yxy050208/multisim-mcp (36 stars, last pushed 4d ago), licensed MIT. It adds 409 tokens to every session, about $0.0016 per session on Opus 5.5. 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 2026-10-28.

Related

multisim-mcp AGENTS.md compared with instructions from other repositories

multisim-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
multisim-mcp AGENTS.mdyxy050208/multisim-mcpInstructions file364d agoMITA409Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode