The latest articles on DEV Community by Sabee Ur Rehman Khan (@sabeekhann). https://dev.to/sabeekhann https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4092772%2F83508bbd-5ef5-49c7-89a0-239265863fa2.jpg https://dev.to/sabeekhann en Sabee Ur Rehman Khan Mon, 24 Aug 2026 17:45:26 +0000 https://dev.to/sabeekhann/i-built-a-local-usage-intelligence-dashboard-for-claude-code-4jh7 https://dev.to/sabeekhann/i-built-a-local-usage-intelligence-dashboard-for-claude-code-4jh7 <h2> How CC Token Meter turns local Claude Code transcripts into token, cost, cache and project-level insights — without sending your data anywhere </h2> <p>AI coding tools are changing how quickly software can be built, but they also introduce a new engineering resource to understand: tokens.</p> <p>Once I started looking at Claude Code usage more closely, I realized that a total token number wasn't particularly useful.</p> <p>I wanted to know:</p> <p>Which project is consuming the most?</p> <p>Which sessions are unusually expensive?</p> <p>Is prompt caching actually working?</p> <p>How is usage changing over time?</p> <p>And most importantly: is there anything I can change?</p> <p>That became CC Token Meter.</p> <p>Instead of intercepting Claude Code requests or introducing another cloud service, CC Token Meter works from the session data Claude Code already stores locally.</p> <p>The architecture is intentionally straightforward:</p> <p>Claude Code transcripts → local parser → private usage index → analytics → local dashboard</p> <p>From there it can derive token and estimated-cost activity, project and branch attribution, cache behavior, historical trends, budgets and optimization insights.</p> <p>The privacy boundary was just as important as the analytics. Transcript access is read-only, the dashboard is loopback-only, no telemetry is collected, and no Anthropic API key is required.</p> <p>The larger idea behind the project is that as AI becomes part of the development stack, AI usage itself needs observability.</p> <p>Not simply a counter showing what was consumed, but tooling that helps engineers understand where resources are going and whether their workflows can be improved.</p> <p>CC Token Meter is open source, and this is still the beginning.</p> <p>GitHub: <a href="https://github.com/Sabeekhann/cc-token-meter" rel="noopener noreferrer">https://github.com/Sabeekhann/cc-token-meter</a></p> ai webdev javascript beginners