Hydraia: Enhance Codex with AI Skill for Feature Management

Hydraia: Enhance Codex with AI Skill for Feature Management

Hydraia is an AI skill designed to enhance the Codex environment by streamlining feature management tasks. It runs a comprehensive spec-driven pipeline to assist in building, adding, implementing, or changing features, handling bug reports, and conducting branch reviews on Codex.

What this skill does

• Triage and analyze feature requests and bug reports raised by users.
• Generates a detailed specification and threat model for proposed changes.
• Facilitates planning and self-review stages to finalize change plans.
• Deploys sub-agents for executing plan tasks efficiently using cost-effective models such as `gpt-5.6-luna`.
• Initiates a double review process using advanced models like `gpt-5.6-sol` for enhanced review quality.
• Verifies implemented changes against the predefined specifications.
• Uses Codex primitives like `apply_patch`, sub-agents, and model routing to organise the workflow effectively.

Who it is for

This skill is tailored for software developers and development teams who utilize AI coding agents like Claude Code, Cursor, or Codex for software development and maintenance. It supports teams aiming for a structured and thorough feature management process within their AI-driven development environments.

Use cases

• A developer seeking to implement a new feature based on a user story or ticket can use Hydraia to guide the process from triage through to verification.
• Teams can leverage Hydraia in managing bug reports, ensuring that issues are thoroughly analyzed and resolved according to a defined specification.
• When conducting branch reviews, Hydraia aids in evaluating proposed changes against existing specifications and threats, ensuring a quality assurance process.

Technical details

• Hydraia operates as a Codex-native pipeline under the host-specific mechanics of the Codex environment.
• Utilizes a `PreToolUse` hook to oversee and synchronize the application of patches after the plan is approved.
• Integrates supporting skills invoked with specific commands to coordinate tasks among sub-agents efficiently.
• Runs sessions using `gpt-5.6-sol` to ensure comprehensive analysis and review capabilities.

Source & Licence

This package is built on open-source work published by jdanigo (jdanigo/hydraia) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.