Clinescope

Clinescope is an independent, unofficial tool - not affiliated with, endorsed by, or sponsored by Cline or Cline Bot Inc. "Cline" is a trademark of Cline Bot Inc., used only to describe compatibility.

Clinescope runs on both the Cline CLI and the VS Code extension. Point it at a CLI trace, or run clinescope --vscode to auto-discover and score a VS Code extension session (see Score a VS Code extension session).

Clinescope is an AI evaluation tool that lives in your Cline development workflow, reads your logs, and helps you write better prompts by checking tool choices, catching messy code rewrites, and ensuring updates don't break past work. Clinescope reads a Cline log and scores four things:

• tool_selection: did the agent call the tools the task needed?
• diff_coherence: are its code patches valid and well-formed?
• diff_minimality: are its edits small and focused, not bloated rewrites?
• apply_recovery: when a patch failed, did the agent fix it?

Why Clinescope

Clinescope scores coding-agent execution traces and ships a code-diff-quality scorer. DeepEval scores tool selection but not code patches or diffs; promptfoo, Langfuse, and Braintrust hand the diff scorer to you; UK AISI's Inspect runs SWE agents but ships no diff-quality scorer. Clinescope's diff_coherence / diff_minimality / apply_recovery scorers are that layer, run against real captured Cline traces (see the validation corpus).

Clinescope validates its own optional LLM judge against human labels and, finding it agrees only at chance level, deliberately keeps it out of the pass/fail gate. See docs/judge-validation.md.

Get Started

1. Install Clinescope

   Requires Python 3.11+. Installing into a virtual environment is recommended.

   pip install clinescope
   

2. Use Clinescope

   Get the score:

   Point Clinescope at a Cline log file (a messages.json trace) to score the run - replace path/to/messages.json below with your own.

   clinescope path/to/messages.json --expected read_files apply_patch
   

   After --expected, list the tools you think the task needed. Run clinescope --list-tools to print the tools in Clinescope.

   Improve your prompt:

   clinescope path/to/messages.json --expected read_files apply_patch --advice
   

Learn more in the usage guide.

New to this? The quickstart walks you from installing Cline to scoring your own session.

Feedback

Ran Clinescope on your own Cline trace? Tell me how it went, what worked, or what was confusing: open a feedback issue and pick "Share feedback". First-run impressions on a real trace are the single most useful thing you can send.

For a reproducible scorer or CLI bug, the Bug report form is a better fit. To contribute a change, see CONTRIBUTING.md for dev setup, tests, and what a scorer change needs.

License

Apache-2.0. Copyright 2026 Tran Binh Minh.