What is LTSpice-MCP AGENTS.md?

A repository guide for AI coding agents working on LTSpice-MCP, a local Python command-line tool and server for generating, simulating, inspecting, and reusing LTspice electronic circuits.

Use it as the entry point for work on the LTspice agent, including project creation, circuit planning, simulation-related changes, and following the project's execution milestones.

It gives agents the project's current purpose, roadmap boundaries, operating rules, and local context in one canonical document. This helps them avoid outdated plans and unsafe or inconsistent changes.

How AbiyuLingga/LTSpice-MCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to AbiyuLingga/LTSpice-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/AbiyuLingga/LTSpice-MCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/AbiyuLingga/LTSpice-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/abiyulingga/ltspice-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/abiyulingga/ltspice-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/abiyulingga/ltspice-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/abiyulingga/ltspice-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/abiyulingga/ltspice-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/abiyulingga/ltspice-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,099 This file is loaded in full into every session.

When invoked 4,099 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.

Model	Per session	Once invoked
Fable 5.1	$0.04099	$0.04099
Opus 5.5	$0.01640	$0.01640
Sonnet 5.5	$0.00820	$0.00820
Haiku 4.5	$0.00410	$0.00410

Measured 2mo ago against content hash 737db11bac94, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LTSpice-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 2mo 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 · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operational guide for AI coding agents working inside this repository. This file is the canonical entry point. CLAUDE.md, OPENCODE.md, and MCP.md are thin shims that point here.

What this project is

ltspice-ai-agent is a local Python CLI plus a local MCP server that lets AI agents safely generate, simulate, inspect, and reuse LTspice circuits. The Python core owns all validation, file generation, and simulation execution. The agent proposes intent, parameters, and topology only.

The active long-term plan lives in docs/AI_HARDWARE_AGENT_ROADMAP.md. docs/PROJECT_PLAN.md remains the historical analog MVP plan. Phase 12 (Tiny8) is complete and the Phase 13 live-editing/Math Core surface is an integrated prototype. New work follows the serialized single-agent milestones in docs/SINGLE_AGENT_EXECUTION_PLAN.md.

Phase 7 (Create Project Workflow) is complete. ltagent create takes either an IR JSON file path or a natural-language prompt, runs the planner, and writes the full project artefact set. Refusal paths return the create.refused structured payload.

Phase 8 (Rule-Based Planner) is complete. ltagent plan "<prompt>" parses a small, deterministic set of English and Indonesian prompts into a validated CircuitIR. See src/ltagent/planner.py and the public API: plan_prompt(text: str) -> CircuitIR | PlannerRefusal. The CLI subcommand mirrors that. Do not introduce an LLM-backed planner before documenting the contract change in an ADR; Phase 8 is intentionally rule-based.

Phase 9 (Template Evaluator / Promoter) is complete. Failed simulation, low layout score, and duplicate value-only templates cannot become official. Promotion is manual via ltagent template promote. The evaluator records the score and gates from plan §15.3.

Phase 10 (MCP Server v1) is complete. ltagent-mcp (after pip install "ltspice-ai-agent[mcp]") runs an stdio MCP server that originally shipped 10 curated tools and 8 curated resources backed by the same Python core. The current integrated surface exposes 27 tools and 16 resources. No run_shell, no execute_python, no generic read_file/write_file, no .raw exposure. See MCP.md and docs/mcp_setup.md.

Read the full file on GitHub · 312 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.

2mo ago First seen · 312 lines · 4,099 tokens per session scan A 737db11bac94

Subscribe to this mod's changes

LTSpice-MCP AGENTS.md is an instructions file published in the GitHub repository AbiyuLingga/LTSpice-MCP (0 stars, last pushed 4mo ago), licensed MIT. It adds 4,099 tokens to every session, about $0.0164 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 2026-08-31.

Hardware and IoT Scientific

LTSpice-MCP AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
LTSpice-MCP AGENTS.mdAbiyuLingga/LTSpice-MCP	Instructions file	0	4mo ago	MIT	A	4,099	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

LTSpice-MCP: Instructions file for Codex