What is local-model-workers-mcp AGENTS.md?

Project instructions for Local Model Workers, a Node.js and TypeScript service that delegates code-related tasks to a privately hosted language model.

They are for configuring the service, understanding its setup and architecture, and following its process for isolated test runs and unapplied patch results.

They explain the required workflow and keep the remote model from directly changing the developer’s repository.

How gaabrielrd/local-model-workers-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to gaabrielrd/local-model-workers-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/gaabrielrd/local-model-workers-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/gaabrielrd/local-model-workers-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/gaabrielrd/local-model-workers-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/gaabrielrd/local-model-workers-mcp/agents-md)

Your own site

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

Per session 1,206 This file is loaded in full into every session.

When invoked 1,206 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	$0.01206	$0.01206
Opus 5.5	$0.00482	$0.00482
Sonnet 5.5	$0.00241	$0.00241
Haiku 4.5	$0.00121	$0.00121

Measured 2mo ago against content hash 97a05b2cff0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-model-workers-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 · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instruções do projeto

Projeto: Local Model Workers MCP — servidor MCP local (Node.js/TypeScript) que delega exploração de repositório, busca semântica, consultas de código, geração de testes, correção de lint e geração de documentação a um modelo servido por LM Studio numa rede privada confiável. O servidor local permanece a fronteira de segurança: o modelo remoto nunca escreve no repositório do desenvolvedor nem aplica patch nele; patches de escrita retornam como diff unificado não aplicado, e comandos de teste só rodam em cópias temporárias isoladas (auto-validate) até passarem ou o limite ser atingido.

O setup interativo (setup/init) escolhe os harnesses por um seletor de checkboxes (setas + Space para alternar, Enter confirma, Ctrl+C cancela), com fallback não interativo via flags como --target all --yes.

Estado atual (main)

Release 3.2.0 publicado (main inclui atribuição por workspace_label via cabeçalhos HTTP, resultados incrementais via since_revision para ferramentas de leitura, roteamento adaptativo de modelos, extração de arestas de chamada no code graph com suporte a impact_of, correções verificadas em sandbox e limpeza das variáveis legadas de provedor — além de cobertura de 12 linguagens, gerenciamento de contexto, SQLite vector storage e circuit breaker resiliency).
Existem exatamente 15 ferramentas MCP (veja docs/mcp-tools.md).
npm run validate roda format:check, lint, check:boundaries, typecheck, build e testes.
Roadmap v3 concluído até a tarefa 065 (v3.3 / release 3.2.0, veja docs/plan-v3.md e docs/roadmap.md).
Versionamento: cada implementação do roadmap vira uma release minor; main avança o minor a cada pilar concluído com npm run validate verde.

Leia primeiro

README.md
docs/architecture.md
docs/development-process.md
docs/testing.md

Processo obrigatório

Entenda a solicitação e os critérios de aceite.
Inspecione os arquivos relevantes e os testes existentes.
Apresente um plano para mudanças que afetam vários arquivos.
Mantenha as alterações dentro do escopo solicitado.
Adicione ou atualize testes para mudanças de comportamento.
Execute npm run validate.
Revise o diff final (escopo, segredos e escrita não intencional).
Atualize a documentação afetada.

Read the full file on GitHub · 111 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 · 111 lines · 1,206 tokens per session scan A 97a05b2cff0f

Subscribe to this mod's changes

local-model-workers-mcp AGENTS.md is an instructions file published in the GitHub repository gaabrielrd/local-model-workers-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,206 tokens to every session, about $0.0048 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.

local-model-workers-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
local-model-workers-mcp AGENTS.mdgaabrielrd/local-model-workers-mcp	Instructions file	1	3mo ago	MIT	A	1,206	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
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

local-model-workers-mcp: Instructions file for Codex