habitat-thinking

Carpaccio slices raw task descriptions into manageable pieces for better decision-making, enhancing project cadence and clarity.

Facilitates the extraction of team conventions into structured, enforceable artefacts, enhancing AI collaboration and output quality.

Facilitates auditing project dependencies for vulnerabilities and supply chain risks, integrating with Go and Maven/JVM for automated scanning.

Architectural fitness functions automate checks for system-wide properties, ensuring architectural integrity and monitoring health over time.

Assesses GitHub Actions workflows for security vulnerabilities and supply chain risks, ensuring CI pipelines are hardened.

Guides governance auditors through audits, detecting semantic drift, and assessing governance constraints for alignment and compliance.

Teaches how to translate governance language into operational constraints for effective compliance and verification in HARNESS.md.

Facilitates drift detection and reporting for configuration files, ensuring alignment with HARNESS.md and improving system reliability.

Enhances observability in harness systems by monitoring health, configuring telemetry, and ensuring effective operational cadences.

Enhances code readability and maintainability by structuring it for human understanding with narrative documentation and logical presentation.

Audits projects for secrets in source control using Gitleaks, ensuring security by detecting sensitive information in code repositories.

Facilitates the creation and interpretation of Mitchell-extended model cards, ensuring accurate and honest representation of model details.

Facilitates rigorous spec reviews by raising objections across six categories, ensuring thorough evaluation before implementation.

Evaluates a team's AI literacy level using the ALCI instrument, providing insights into their AI collaboration capabilities.

Guides users in designing and implementing constraints within the HARNESS framework for effective rule enforcement and verification.

Context engineering enhances LLM performance by structuring project conventions and documentation for effective codebase interaction.

Syncs HARNESS.md conventions across Cursor, Copilot, and Windsurf, ensuring consistent project rules for AI coding tools.

Audits Docker images for vulnerabilities and provides remediation recommendations, enhancing security in containerized applications.

Guides users on implementing garbage collection rules to maintain code quality and prevent decay in software projects.

Generates a prioritized improvement plan for AI literacy based on user assessment, mapping gaps to specific actions.