review
01Agent Claude Code
Architectural code reviewer for codealmanac. Use after meaningful code changes, before merging, or whenever code shape feels off.
50 tagged codebase, measured the same way as everything else here.
Browse within: docker 28graph-algorithms 28graph-api 28graph-database 28graph-embedding 28coding-agents 19ai-agents-framework 18code-visualization 18knowledge-graph 18ontology 18
Agent Claude Code
Architectural code reviewer for codealmanac. Use after meaningful code changes, before merging, or whenever code shape feels off.
Agent
With Lessons from claudette-debug, claudette-auto & Advanced Discipline Principles.
Agent
Claudette PM Agent v1.2.0 (Project Manager & Requirements Analyst).
Agent
Claudette Research Agent v2.0.0 (Memory-Enhanced Research & Analysis Specialist - Mimir Edition).
Agent Codex
Head of the PO Council and eight-seat design bench. Owns whether to convene, seat selection, order, named conflict rules, and the decision record; never edits code.
Agent Codex
Accountable design decider and applier. Reviews real UI evidence, rejects token drift and generic AI styling, prescribes exact changes, edits code, and remeasures the result.
Agent Codex
Motion / Action Designer on the Atlas bench. Combines physical feel, interruption continuity, distance-aware timing, frame measurement, and reduced-motion equivalents.
Agent Claude Code
Start codebase analysis. Analyze single entity/action only. Return detailed analysis, recommendations, implementation guidance, usage examples. Prefer dependencylibraries-related-files-search first. Provide all relevant context (files, paths, symbols, imports, etc.). One topic or one context per request → wait for the…
Agent Claude Code
Return the public names of local libraries/codebases available for analysis. Provide dependencylibraries-related-files-search and/or dependencylibraries-analysis with an approptiate name from this list.
Agent Claude Code
Start related-file discovery. Find files relevant to single entity/action before dependencylibraries-analysis. Provide all relevant context (files, paths, symbols, imports, etc.). One topic or one context per request → wait for the result → send the next request! Instead "Find X, Y, Z, etc." you MUST "Find X.", wait…