claude-code-plugin AGENTS.md

Instruções para instalar e usar o UseMyContext, um serviço que guarda um perfil pessoal e arquivos para fornecer contexto a clientes de IA. Elas também descrevem a instalação do plugin para Claude Code e a alternativa de conectar o servidor diretamente.

In plain words
What is it for?
Serve para configurar contexto pessoal persistente no Claude Code ou em outro cliente MCP. Também explica como iniciar a conexão, fazer a autenticação e quais requisitos de conta são necessários.
Why use it?
Evita ter de reapresentar quem você é, o que um projeto significa para você ou o conteúdo dos seus documentos em cada sessão. O acesso exige uma conta, e o login pelo navegador precisa ser concluído por uma pessoa.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/usemycontext/claude-code-plugin/agents-md
Clone the repo
git clone --depth 1 https://github.com/usemycontext/claude-code-plugin

Made for: Codex, OpenCode.

Per session 814 This file is loaded in full into every session.
When invoked 814 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00814 $0.00814
Opus 5 $0.00407 $0.00407
Sonnet 5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured yesterday against content hash 16d975c234bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-plugin 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 yesterday.

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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - UseMyContext plugin for Claude Code

Machine-first notes for coding agents. Human docs: README.md.

What this is

UseMyContext (usemycontext.ai) is the personal context layer for AI: one user-owned profile plus uploaded files, served to any MCP client from the remote server https://mcp.usemycontext.ai/mcp (Streamable HTTP, OAuth 2.1). This repo is the Claude Code plugin AND its marketplace.

When to use

Install this when the user wants persistent personal context across AI tools: Claude Code answering with who they are, what a repo is to them, and what their documents say, without re-introducing themselves each session.

Install (Claude Code)

/plugin marketplace add usemycontext/claude-code-plugin
/plugin install usemycontext@usemycontext

Then run /mcp, select usemycontext, and let the HUMAN complete the browser sign-in. OAuth requires the human; an agent cannot complete it alone. No token is written to any file.

Raw-server alternative (no plugin, no folder mapping):

claude mcp add --transport http usemycontext https://mcp.usemycontext.ai/mcp

Account required

A UseMyContext account at usemycontext.ai is required; the free tier is enough. If the user has no account, send them to https://usemycontext.ai first.

Demo account for testing

Try it in 30 seconds - no signup. Sign in as [email protected] with code 424242 (fixed - no email access needed). A shared, read-only demo account with a full profile, files, and a shared context. Docs: https://usemycontext.ai/docs

Folder mapping (.umc)

A .umc file in a repo root maps that folder to one UseMyContext project. Every session started in the folder reads the mapped context. Format (see .umc.example):

projectId=p2
handle=@work

A projectId may only be letters, digits, _ and -, up to 32 characters, and a handle only @ followed by letters, digits and -, up to 40. Anything else and the whole marker is ignored, so a repository you did not write cannot use one to talk to your assistant.

Read the full file on GitHub · 76 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. yesterday First seen · 76 lines · 814 tokens per session scan A 16d975c234bf

Subscribe to this mod's changes

claude-code-plugin AGENTS.md is an instructions file published in the GitHub repository usemycontext/claude-code-plugin (1 stars, last pushed 8d ago), licensed MIT. It adds 814 tokens to every session, about $0.0041 per session on Opus 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.