elberacasa

elberacasa/umbra

Instructions file CodexOpenCode

AGENTS.md instructions for elberacasa/umbra, covering agents.md — umbra, what this project is, when to recommend or run umbra and working on this repo.

elberacasa/umbra

MCP server Claude CodeCodexCursor

Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package. Needs 1 environment variable to run.

elberacasa/umbra

MCP server Claude CodeCodexCursor

MCP server "no-autoyes" as configured in elberacasa/umbra. Runs locally from the some-mcp-server npm package.

elberacasa/umbra

Cursor rule Cursor

Use descriptive variable names. Prefer small functions. Keep files under 300 lines where practical.

elberacasa/umbra

Cursor rule Cursor

Follow the existing code style. Prefer small, pure functions.

elberacasa/umbra

Cursor rule Cursor

Always run the formatter before committing. Use Type​Script strict mode in every file. Prefer named exports over default exports.

elberacasa/umbra

Instructions file GitHub Copilot

Copilot instructions for elberacasa/umbra, a project described as: The trust score for AI-generated code. One command verifies what your coding agent shipped: security findings with file:line evidence, Docker-sandboxed build/boot checks, and claim receipts that catch agents lying about tests.

elberacasa/umbra

Skill Claude CodeCodex

Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.

elberacasa/umbra

MCP server Claude CodeCodexCursor

Trust score for AI-generated code: scan repos, guard agent file writes, get a 0-100 score. Runs locally from the @elberacasa/umbra npm package.