Inquiry

Analyze. Plan. Execute.

Currently available for GitHub Copilot. More targets coming soon.

v0.3.0

Public entry surface. For the canonical documentation map, start in the repository docs.

PowerShell irm https://inquiry.ccisne.dev/install.ps1 | iex

Installs to %LOCALAPPDATA%\inquiry\, adds to PATH, and deploys Inquiry agents to your AI coding tool.

Inquiry finite state machine diagram showing IDLE → ANALYZE → PLAN → EXECUTE → END → IDLE cycle, with backward transitions and opt-in EVOLUTION state.

Inquiry structures AI-assisted work as a finite-state system with an explicit END gate and optional EVOLUTION pass. Inquiry names the cycle-level process, APE names the orchestrating methodology, and the Finite APE Machine names the engineered system that operationalizes both. The bet is methodology over model: if the framework carries the weight, a smaller or free model following it should stay useful where freestyling falls apart.

The phases

ANALYZE

Clarify the problem. Capture requirements, assumptions, and edge cases before any code is written.

diagnosis.md

PLAN

Decompose the work. Order the steps, verify each, enumerate nothing missed.

plan.md

EXECUTE

Implement under the constraints of the tests. Each change small enough to merge confidently.

code + commits

Backward transitions from PLAN or EXECUTE back to ANALYZE are allowed — re-analysis is part of the contract.

Quick start

# verify prerequisites (inquiry, git, gh, gh auth)
iq doctor

# deploy Inquiry agent + skills to your AI tool (Copilot today)
iq target get

# scaffold .inquiry/ in your repo
cd your-repo && iq init

Commands

12 commands total — see the full table on GitHub.

Targets

Inquiry deploys agent prompts and skills to the global configuration of your AI coding tool.

Adapters for Claude, Codex, Crush, and Gemini already exist — awaiting a stable agent prompt API before being wired in (ADR D20).

Go deeper