endor-project-retrieval-bundle

Build a deterministic retrieval bundle for one Endor Labs project with indexed versions and dependency artifacts.

4|Updated Oct 18, 2025
One-click install
npx skills add https://github.com/endorlabs/endorlabs-sdk --skill endor-project-retrieval-bundle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: endor-project-retrieval-bundle
Source: https://github.com/endorlabs/endorlabs-sdk/tree/main/agent-knowledge/skills/endor-project-retrieval-bundle
Command: npx skills add https://github.com/endorlabs/endorlabs-sdk --skill endor-project-retrieval-bundle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill creates a deterministic, machine-readable retrieval bundle for one Endor Labs project so you can inspect dependencies, scan context, and optional call-graph data without manually stitching artifacts together.

Core Features & Use Cases

  • Single-project export: Produces a versioned context bundle for one project using endor-agent-context.
  • Multi-pass retrieval: Supports index, hydrate, and optional call-graph export passes for progressive disclosure.
  • Targeted analysis: Helps with SBOM slices, DependencyMetadata review, optional session summaries, and call-graph search preparation.
  • Clear handoff boundaries: Explicitly separates project-level retrieval from namespace topology and blast-radius analysis.

Quick Start

Ask the skill to generate a retrieval bundle for one Endor Labs project and return the context manifest path.

Frequently Asked Questions about endor-project-retrieval-bundle

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

FAQPage Schema
How do I build a retrieval bundle for a single Endor Labs project?

To build a retrieval bundle, this Skill performs deterministic, multi-pass retrieval using endor-agent-context to produce a versioned context manifest with indexed versions and hydrated dependency artifacts for one project.

What is a project retrieval bundle used for in dependency analysis?

A project retrieval bundle packages indexed versions, hydrated dependency metadata, and optional call-graph data into a machine-readable format for single-repository inspection, SBOM review, and downstream provenance workflows.

Can I export a call graph from Endor Labs dependency metadata?

Yes, you can export a call graph by enabling the optional call-graph export pass during the multi-pass retrieval process, which adds the call-graph data directly into your single-project retrieval bundle.

Does the retrieval bundle include SBOM slices and session summaries?

Yes, the retrieval bundle supports SBOM slices and DependencyMetadata review, while optional session summaries can be included alongside indexed versions and hydrated dependency artifacts during the export.

What are the limitations of single-project retrieval bundles?

This Skill is limited to single-project export and explicitly separates project-level retrieval from namespace topology and blast-radius analysis, requiring strict manifest-first parsing and bounded multi-pass selection within export limits.

Do I need manifest-first parsing to generate Endor Labs dependency metadata?

Yes, strict manifest-first parsing is required to generate the deterministic retrieval bundle, ensuring bounded multi-pass selection and explicit handling of project scope and namespace disambiguation.