agentmods.dev

Tool_MCP_LMStudio: Instructions file for Codex

AGENTS.md

Tool_MCP_LMStudio AGENTS.md is an instructions file for Codex, OpenCode from Ka1y0/Tool_MCP_LMStudio. It costs 1,218 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for maintaining lmstudio-mcp, a local server that connects coding agents to LM Studio. It covers the project mission, architecture, safety rules, and commands.

In plain words
What is it for?
Use it when working on the server's TypeScript entry points, configuration, LM Studio client, diagnostics, benchmarks, logs, tool calling, streaming, or capability snapshots.
Why use it?
It gives agents project-specific rules for keeping the server local, preventing cloud fallback and implicit downloads, and avoiding broad changes to the machine.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is Ka1y0/Tool_MCP_LMStudio's own configuration. It tells Codex and OpenCode how to work on Tool_MCP_LMStudio 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 Tool_MCP_LMStudio configures →

not rated 0repo 2mo ago A scan 1,218 tokens original MIT
View source ↗ Ka1y0/Tool_MCP_LMStudio
Reuse

Borrowing it

Nothing to install: this file belongs to Ka1y0/Tool_MCP_LMStudio. 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/Ka1y0/Tool_MCP_LMStudio/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Ka1y0/Tool_MCP_LMStudio

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 Tool_MCP_LMStudio AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ka1y0/tool_mcp_lmstudio/agents-md/github.svg)](https://agentmods.dev/instructions/ka1y0/tool_mcp_lmstudio/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ka1y0/tool_mcp_lmstudio/agents-md"><img src="https://agentmods.dev/badge/instructions/ka1y0/tool_mcp_lmstudio/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 Tool_MCP_LMStudio AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ka1y0/tool_mcp_lmstudio/agents-md"><img src="https://agentmods.dev/badge/instructions/ka1y0/tool_mcp_lmstudio/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,218 This file is loaded in full into every session.
When invoked 1,218 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 $0.01218 $0.01218
Opus 5.5 $0.00487 $0.00487
Sonnet 5.5 $0.00244 $0.00244
Haiku 4.5 $0.00122 $0.00122

Measured 2mo ago against content hash 442dae2f5903, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Tool_MCP_LMStudio 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Mission

Maintain lmstudio-mcp as a production-quality, local-only MCP stdio server. It diagnoses and exercises LM Studio without cloud fallback, telemetry, implicit downloads, or broad machine mutations.

Architecture

  • src/index.ts: stdio entrypoint; stdout is reserved for MCP protocol frames.
  • src/server.ts: constructs the MCP server and registers tools.
  • src/config.ts: environment parsing and mandatory loopback restriction.
  • src/lmstudio/api.ts: abortable native/OpenAI-compatible HTTP client and response parsing.
  • src/lmstudio/cli.ts: spawn-based lms wrapper using argument arrays.
  • src/lmstudio/diagnostics.ts: health, model, endpoint, and MCP config checks.
  • src/lmstudio/benchmark.ts: small streaming benchmarks.
  • src/lmstudio/logs.ts: bounded log process lifecycle and redaction.
  • src/lmstudio/toolCalling.ts: deterministic real tool-call parsing, validation, execution, delivery, and continuation checks.
  • src/lmstudio/streamingToolCalling.ts: streamed tool-call delta assembly, progress, cancellation, and continuation verification.
  • src/lmstudio/capabilitySnapshot.ts: canonical, hashed, secret-free capability snapshots.
  • src/lmstudio/structuredOutput.ts: endpoint-mode detection, fenced/raw JSON parsing, and Ajv JSON Schema validation.
  • src/lmstudio/capabilityEvidence.ts: process-local verified evidence; never persist capability claims as facts.
  • src/lmstudio/capabilities.ts: strict DECLARED/DETECTED/VERIFIED synthesis.
  • src/lmstudio/securityAudit.ts: read-only local security inspection.
  • src/toolDocumentation.ts: operational metadata merged into the generated LLM tool reference.
  • src/toolReference.ts: introspects the real MCP registry and builds docs/mcp-tools.json.
  • llms.txt and docs/LLM_USAGE.md: LLM routing index and canonical agent operating manual.
  • src/tools/: Zod schemas and MCP registrations grouped by responsibility.
  • tests/unit: isolated security and validation tests.
  • tests/integration: live LM Studio tests that skip when unavailable.
  • tests/mcp: official MCP SDK stdio initialize/list/call smoke test.
  • scripts/run-node-tool.sh: portable system-Node launcher with a Codex bundled-runtime fallback.

Read the full file on GitHub · 91 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.

  1. 2mo ago First seen · 91 lines · 1,218 tokens per session scan A 442dae2f5903

Subscribe to this mod's changes

Tool_MCP_LMStudio AGENTS.md is an instructions file published in the GitHub repository Ka1y0/Tool_MCP_LMStudio (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,218 tokens to every session, about $0.0049 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.

Building agentsai-agentscodexlmstudiolocal-llmmcpmodel-context-protocol
Related

Tool_MCP_LMStudio AGENTS.md compared with instructions from other repositories

Tool_MCP_LMStudio AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Tool_MCP_LMStudio AGENTS.mdKa1y0/Tool_MCP_LMStudioInstructions file02mo agoMITA1,218Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot