oracle

Bundle repository files with a prompt for context-grounded codebase analysis.

Updated May 8, 2026
One-click install
npx skills add https://github.com/freire19/Mythos --skill oracle-freire19
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/freire19/Mythos/tree/main/skills/oracle
Command: npx skills add https://github.com/freire19/Mythos --skill oracle-freire19

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of getting useful, repository-grounded answers by bundling a targeted set of files with your prompt into a one-shot request that preserves real context.

Core Features & Use Cases

  • Best-practice one-shot bundling: Combines your prompt with carefully selected repo files for a model to answer with concrete context.
  • Engine workflows (browser vs API): Supports a long-running browser workflow for models like GPT-5.2 Pro and an API mode for other provider needs.
  • Token- and session-aware execution: Uses dry-run previews, file reports, and reattachable sessions to avoid wasted reruns and to manage timeouts.
  • Safe attachment patterns: Applies include/exclude globs, respects .gitignore, filters dotfiles by default, and rejects overly large files.

Quick Start

Run oracle with browser engine mode, attach the smallest file set that contains the truth, and use the generated one-shot context for an advisory repo-grounded answer.

Frequently Asked Questions about oracle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I bundle repository files with a prompt for accurate codebase analysis?

Yes, you can run long-running code auditing sessions by using reattachable session management. This prevents wasted reruns and manages timeouts during extended repository analysis workflows.

How do I safely select files for context bundling without including unnecessary repository artifacts?

Safely select files for context bundling by applying include/exclude file globbing patterns. The process honors .gitignore rules, filters dotfiles by default, and rejects overly large files to ensure safe attachment patterns.

What's the best way to preview a one-shot context bundle before sending it to a model?

The best way to preview a one-shot context bundle is by running a dry-run preview. This generates a file report that helps you verify the selected repository artifacts and manage token limits before execution.

Does context bundling work with browser engines for code auditing tasks?

Yes, context bundling supports browser engine workflows for one-shot execution alongside an optional API mode. This allows models to reason over real local artifacts during code auditing and vulnerability research.

Why do my repository-grounded answers lack specific code context during debugging?

Repository-grounded answers lack specific code context when you do not bundle a focused set of local files with your prompt. Attaching the smallest file set containing the truth ensures concrete, context-grounded model responses.