Code Health MCP
Structural code health via CodeScene MCP: review before edits, verify score deltas, gate commits and PRs.
- What
- Structural code health via CodeScene MCP: review before edits, verify score deltas, gate commits and PRs.
- Cost
- Free
- Needs
- Use "Code Health MCP" with your Muse.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: structural maintainability feedback for AI-assisted coding through the CodeScene MCP server, complementing style linters with design-level health scores and regression gates. The loop is strict: run code_health_review before touching a file to record a baseline score plus the listed code smells, make the smallest change that addresses the task, then run code_health_score after each edit and never mark the task done while the score sits below its baseline. Before every commit, pre_commit_code_health_safeguard blocks regressions; before a PR, analyze_change_set checks the whole branch. Scores run 1 to 10 (green at 9+, yellow from 4 to 8.9, red below 4) with scope rules per range: below 5 means minimal diffs only, 5 to 7 means no broad refactors. Includes a paste-ready AGENTS.md enforcement block and pairing guidance with verification loops, TDD workflows, and security reviews (tests passing does not mean the design is healthy). By @affaan-m, listed here with credit to its creator. From the affaan-m/ECC repository (MIT). Honest caveats: requires the CodeScene MCP server plus your own CS_ACCESS_TOKEN (see the prerequisites in the install prompt); standalone mode needs no paid CodeScene platform account for the four tools. If the MCP is unavailable, the skill instructs to skip the check rather than invent scores. Do not point it at secrets, credentials, or paths you would rather not have analyzed. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseWe automatically scan every listing and flag anything suspicious, but we can't review every line of community code. Here's how to check a build yourself before you install it.
Use "Code Health MCP" with your Muse. Prerequisites: a CodeScene personal access token (CS_ACCESS_TOKEN), which you create yourself in the upstream codescene-mcp-server repo (link in the skill). Set it as an environment variable, never commit it. Standalone mode needs NO paid CodeScene platform account for the four tools below. The Muse app (mobile or web) for the planning side, plus a local code checkout the MCP can analyze. 1. Open the skill: https://github.com/affaan-m/ECC/blob/main/skills/codehealth-mcp/SKILL.md and copy the full SKILL.md text. 2. Install the MCP server: copy the "codescene" entry from the skill into your harness MCP config (command: npx -y @codescene/codehealth-mcp, env CS_ACCESS_TOKEN set). Restart the session and confirm the server is connected before relying on scores. 3. Paste the skill into a chat with Muse and add: "Review the Code Health of [file or directory] before I change it: [path]." Tip: scope your edits by the score. Below 5, keep diffs minimal; 5 to 7, no broad refactors. And never declare a task done while the score is lower than when you started. Safety: a skill is plain-text instructions; it runs nothing by itself. If the MCP is unavailable, skip the check rather than inventing scores. Never paste secrets into a chat, and review anything Muse proposes before it acts.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.