Skip to main content

AI-assisted development context management tool for maintaining consistency and productivity

Project description

Quaestor

🏛️ Context management for AI-assisted development

PyPI Version Python 3.8+ License: MIT Documentation

Quaestor transforms AI-assisted development through specification-driven workflows, intelligent agent orchestration, and streamlined context management for Claude Code.

Key Features

  • 🎯 Specification-Driven Development - Clear contracts with acceptance criteria and lifecycle management
  • 🤖 13 Specialized AI Agents - Expert agents including new speccer for YAML generation
  • 🔄 Smart Automation Hooks - Automatic spec validation and progress tracking
  • 40% Faster Context Loading - Consolidated templates for better performance
  • Specification Validation - Built-in quaestor validate command for spec files

Quick Start

Using uvx (Recommended - No Installation Required)

# Initialize Quaestor without installing it
uvx quaestor init

# Team mode - shared configuration
uvx quaestor init --mode team

# Update to latest version
uvx quaestor update

Traditional Installation

# Install globally
pip install quaestor

# Initialize project
quaestor init

# Create your first specification
/plan "User Authentication System"

# Implement the specification
/impl spec-auth-001

Project Modes

Personal Mode (Default)

Perfect for individual projects:

quaestor init
  • Commands installed globally in ~/.claude/commands/
  • Local settings in .claude/settings.local.json (not committed)
  • Project files in .quaestor/ (gitignored)
  • CLAUDE.md with project-specific context

Team Mode

For shared projects with consistent standards:

quaestor init --mode team
  • Commands in .claude/commands/ (committed, shared with team)
  • Settings in .claude/settings.json (committed)
  • Project files in .quaestor/ (committed)
  • CLAUDE.md with team standards and context

Key Difference: Personal mode keeps configuration local, Team mode shares everything with the team.

Core Commands

  • /plan "Feature Name" - Create specification with clear contracts
  • /impl spec-id - Implement according to specification
  • /research "topic" - Analyze codebase patterns and architecture
  • /review spec-id - Validate implementation quality
  • /debug "issue" - Systematic debugging and fixes
  • quaestor validate spec.yaml - Validate specification file structure

How It Works

Specification-First Development

  1. Plan with Contracts - /plan creates detailed specifications with input/output contracts
  2. Lifecycle Management - Specs move through draft/active/completed/ folders
  3. Agent Orchestration - 13 specialized agents collaborate on implementation
  4. Quality Assurance - Built-in testing and review workflows with automatic validation

Example Workflow

# 1. Create specification
/plan "JWT Authentication API"
# → Creates spec-auth-001.yaml in draft/ folder

# 2. Implement with guided workflow
/impl spec-auth-001  
# → Moves to active/, orchestrates architect → implementer → qa agents

# 3. Review and deploy
/review spec-auth-001
# → Validates quality, moves to completed/ when done

Hook System

Quaestor's hooks integrate seamlessly with Claude Code using uvx, requiring no local installation:

  • Session Context Loader - Automatically loads active specifications at session start
  • Progress Tracker - Updates specification progress when TODOs are completed
  • Spec Validator - Validates specification YAML files on save (blocks on errors)
  • No Python Required - Hooks run via uvx without installing Quaestor in your project

The hooks are configured in .claude/settings.json and execute Quaestor commands remotely via uvx.

Documentation

📚 Full Documentation

Contributing

git clone https://github.com/jeanluciano/quaestor.git
cd quaestor
pip install -e .
pytest

License

MIT License


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

quaestor-0.6.3.tar.gz (142.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

quaestor-0.6.3-py3-none-any.whl (148.1 kB view details)

Uploaded Python 3

File details

Details for the file quaestor-0.6.3.tar.gz.

File metadata

  • Download URL: quaestor-0.6.3.tar.gz
  • Upload date:
  • Size: 142.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for quaestor-0.6.3.tar.gz
Algorithm Hash digest
SHA256 20b1830c6e569e91e4417154f70e2e34d739ff463dda902798f9ebb9b25b6bea
MD5 c08ad7bfa8e082f009120aa241a1e87d
BLAKE2b-256 609e854cad11156884db1099627d8159e24e588e9713c781f52c6e9a9b3ebe16

See more details on using hashes here.

Provenance

The following attestation bundles were made for quaestor-0.6.3.tar.gz:

Publisher: publish.yml on jeanluciano/quaestor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file quaestor-0.6.3-py3-none-any.whl.

File metadata

  • Download URL: quaestor-0.6.3-py3-none-any.whl
  • Upload date:
  • Size: 148.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for quaestor-0.6.3-py3-none-any.whl
Algorithm Hash digest
SHA256 11194a8b280629c8b3068bd76bfba3cb7516b048d51dde8d523bddc8304b94aa
MD5 36888df1a53398593c0c85a48e0ce22c
BLAKE2b-256 14551bb884344acb8a2b6bdddcf872d4f87ffa256588b6d9121b2c36b06512b9

See more details on using hashes here.

Provenance

The following attestation bundles were made for quaestor-0.6.3-py3-none-any.whl:

Publisher: publish.yml on jeanluciano/quaestor

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page