claudna

Code quality reviewer. Evaluates implementation for correctness, clean design, test coverage, and maintainability.

Analytics engineering agent. Writes, reviews, and tests dbt models against Snowflake.

SRE agent for Modal infrastructure. Diagnoses production issues with serverless GPU workloads.

Data analysis agent for Neon PostgreSQL. Queries via psql and provides insights.

SRE agent for Railway infrastructure. Diagnoses production issues and analyzes deployments.

Use when you want to save, read, or organize persistent notes across Claude sessions.

Use when you want to check whether a /forge plan document is structurally complete, internally consistent, and ready for implementation. Catches missing sections, incomplete frontmatter, unsized phases, vague validation criteria, undocumented decision forks, and cross-reference gaps.

Use when you want to check whether a plan or implementation PR has prior art in the project's history. Searches git history, closed PRs, closed issues, and planning archives for previous attempts at the same problem — surfacing what was tried, what succeeded or failed, and whether the current plan learns from or repeats past approaches.

Use when you have specific product issues to triage or want to discover enhancement opportunities through gap analysis. Supports --output github to create issues and --output session for chat-only analysis.

Architecture-aware product vision — explores what a codebase could become by analyzing existing infrastructure, identifying 1-2 hop features, grouping compound plays, and aligning to a project mission. Replaces /product-brainstorm. Supports --auto and --output github.

5 hooks across 4 events