sdd-explore

Investigates codebases and produces structured exploration analyses for spec-driven development changes.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/AD-Paladins/beaconator-web --skill sdd-explore-ad-paladins
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdd-explore
Source: https://github.com/AD-Paladins/beaconator-web/tree/main/.config/opencode/skills/sdd-explore
Command: npx skills add https://github.com/AD-Paladins/beaconator-web --skill sdd-explore-ad-paladins

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Before committing to a code change, teams need to understand the current architecture, affected files, and trade-offs between approaches. This Skill performs that investigation as a dedicated sub-agent and returns a structured analysis instead of ad-hoc guesses. ## Core Features & Use Cases - Codebase Investigation: Reads entry points, related functionality, tests, and existing patterns to map the current state and affected areas. - Approach Comparison: Compares multiple implementation options with pros, cons, and effort estimates, then gives a recommendation with risks. - Artifact Persistence: Saves an exploration.md artifact tied to a named change across engram, openspec, hybrid, or none storage modes. - Use Case: An orchestrator asks whether to add caching to an API layer; the sub-agent reads the relevant modules, compares two caching strategies, and returns a structured exploration report with a recommendation. ## Quick Start Ask the orchestrator to launch an sdd-explore exploration on a topic such as adding retry logic to the payment service.

Frequently Asked Questions about sdd-explore

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

FAQPage Schema
How do I explore a codebase before making a change in spec-driven development?▼

Delegate the topic to the sdd-explore sub-agent through the orchestrator. It reads relevant code, compares approaches with pros and cons, and returns a structured exploration report with a recommendation and risks.

What does the sdd-explore sub-agent return to the orchestrator?▼

It returns a fixed Markdown structure containing current state, affected areas with file paths, compared approaches with effort estimates, a recommendation, risks, and a ready-for-proposal verdict.

Can sdd-explore modify code during exploration?▼

No. The sub-agent is read-only and may only create an exploration.md file inside the change folder when a change name is provided. It never modifies existing code or files.

Which artifact storage modes does sdd-explore support?▼

It supports engram, openspec, hybrid, and none modes. Engram saves under sdd/{change-name}/explore, openspec follows the openspec convention files, hybrid does both, and none returns the result only.

When should I not use an exploration sub-agent?▼

Skip it for trivial changes where the affected code and approach are already obvious. Exploration adds value when multiple approaches exist, the codebase area is unfamiliar, or risks need to be documented before a proposal.