sdd-explore

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

Updated May 24, 2026
One-click install
npx skills add https://github.com/etrigan16/v0-cipher-ar --skill sdd-explore-etrigan16
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdd-explore
Source: https://github.com/etrigan16/v0-cipher-ar/tree/main/.opencode/skills/sdd-explore
Command: npx skills add https://github.com/etrigan16/v0-cipher-ar --skill sdd-explore-etrigan16

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 exploration report instead of ad-hoc guesses. ## Core Features & Use Cases - Codebase Investigation: Reads entry points, related functionality, tests, and dependencies to map the current state of the system. - Approach Comparison: Produces a pros/cons/effort comparison table when multiple implementation approaches exist. - Structured Artifact Persistence: Saves an exploration.md artifact per change using engram, openspec, hybrid, or none storage modes. - Use Case: An orchestrator agent receives a feature request, delegates exploration to this sub-agent, and gets back a report listing affected files, candidate approaches, risks, and a readiness verdict for the proposal phase. ## Quick Start Ask the orchestrator to explore how a proposed feature would affect the codebase before writing a proposal.

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, identifies affected files, compares approaches, and returns a structured exploration report with a recommendation and risks.

What does the sdd-explore skill produce as output?▼

It returns a structured markdown analysis containing current state, affected areas, approach comparisons with effort estimates, a recommendation, risks, and a ready-for-proposal verdict. When tied to a named change, it also writes an exploration.md artifact.

Can sdd-explore modify code during investigation?▼

No. The skill is strictly read-only for existing code. The only file it may create is exploration.md inside the change folder when a change name is provided.

What artifact storage modes does sdd-explore support?▼

It supports four modes: engram (saves to sdd/{change-name}/explore), openspec (follows openspec conventions), hybrid (persists to both), and none (returns the result only without persistence).

Why does sdd-explore refuse to run when loaded by the orchestrator?▼

The skill has an orchestrator gate: when loaded via the skill tool, the orchestrator must delegate to the dedicated sdd-explore sub-agent instead of executing the instructions inline. Only the executor sub-agent runs the exploration steps.