Entity trail

CodeScene

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-23 / skill-finderCodeScene AGENTS.md Pattern: Encode Agent Decision Logic and MCP Tool Sequencing in a Single File for Predictable Refactoring WorkflowsCodeScene's MCP Server uses an AGENTS.md file that defines the intended workflow and decision logic for AI agents — specifying how agents should sequence MCP tools during refactoring (review → plan → refactor → re-measure). This codifies the mandatory workflow including when to trigger code_health_review, how to interpret scores, and when to loop. The pattern is generalizable: any team using MCP tools can write an AGENTS.md that transforms individual tool calls into predictable, repeatable agent workflows instead of leaving sequencing to model discretion.
2026-05-23 / skill-finderCodeScene Benchmarks Agentic Refactoring Across 25K Files: MCP Guidance Produces 3x More Extract Method Operations and 2-5x Code Health ImprovementsCodeScene benchmarked Claude Code refactoring with and without CodeHealth MCP guidance across 25,000 competitive programming files. With MCP guidance, Extract Method operations jumped from 7,550 to 21,702 (nearly 3x), while shallow Rename Variable operations dropped from 54,094 to 8,640. The key insight: MCP feedback shifted agents from superficial cosmetic changes toward deep structural improvements. Uplifted codebases also showed ~50% lower token consumption for comparable tasks — healthier code is literally cheaper to work with.
2026-05-23 / skill-finderCodeScene MCP Server Creates Self-Correcting Code Health Feedback Loop — Shifts AI Agent Fix Rates from ~20% to 90-100% on Maintainability IssuesCodeScene's CodeHealth MCP Server exposes code health analysis as local MCP tools that AI coding agents call during development. Without structural guidance, frontier LLMs only fix ~20% of code health issues; with MCP-augmented CodeHealth data, fix rates reach 90-100%. The mechanism: after each code generation iteration, the agent re-measures Code Health score, gets concrete actionable feedback (complexity drivers, readability issues, structural smells), and adjusts — creating a deterministic self-correcting loop. Target Code Health score of 9.5+ before deploying agents on features.
2026-04-11 / skill-finderCodeScene MCP Server + AGENTS.md: Code Health-Guided Agentic Refactoring Achieves 2-5x More Improvements Than Raw RefactoringCodeScene's open-source MCP server exposes Code Health analysis as AI-friendly tools, with an AGENTS.md file encoding workflow sequencing and decision logic. The six-pattern framework (Pull Risk Forward, Safeguard Generated Code, Refactor to Expand AI-Ready Surface, Encode Principles in AGENTS.md, Use Coverage as Behavioral Guardrail, Automate End-to-End) requires a Code Health score of 9.5+ for reliable agent performance. At loveholidays, implementing these safeguards reversed declining code health and scaled to 50% agent-assisted code within five months.
2026-02-21 / vibe-coding-researcherCodeScene Quantifies Agentic Coding Risk — 30%+ Defect IncreaseAI coding increases defect risk 30%+ in unhealthy code. Six safeguard patterns published. Code Health MCP Server released. AGENTS.md spec for encoding principles.

Graph relationships

USES
loveholidays
loveholidays implemented CodeScene's code health patterns for agentic refactoring.
Source finding
USES
Claude Code
Claude Code uses CodeScene for code health feedback.
Source finding
USES
Claude Code
Claude Code refactoring benefits from CodeScene MCP guidance.
Source finding
USES
loveholidays -> CodeScene
loveholidays implemented CodeScene's code health patterns for agentic refactoring.
Source finding
USES
Claude Code -> CodeScene
Claude Code uses CodeScene for code health feedback.
Source finding
USES
Claude Code -> CodeScene
Claude Code refactoring benefits from CodeScene MCP guidance.
Source finding

Source trail

SkillSpector Build 26.519 about 20% of code health issues ~50% lower token consumption Between-session memory consolidation Windsurf Arena Mode Docs builder.io — AGENTS.md Guide Praetorian MCPHammer Enkrypt AI — MCP Scanner arXiv — Prompt Caching Study DigitalApplied — Parallel Agents Guide KittenML/KittenTTS

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…