Comet Adds Coding-Agent Cost Tracking in Opik

Comet said it added coding-agent cost tracking to Opik to give engineering leaders real-time visibility into Claude Code and Codex spending by engineer, team, and task. The company framed the update as a response to difficulty tracking AI coding costs as usage scales.

Comet said the questions engineering leaders faced included per-engineer and per-team spend, how that spend mapped to work such as new features and bug fixes, and whether tokens were going to MCPs, skills, and plugins that did not map to needed activity. It also said that with both tools billing at full API rates, the reporting became tied to budget conversations.

In Opik, Comet described a view that tracked spend per engineer, per team, and per task in real time, before an invoice arrived. Comet also said Opik included automated cost optimization that eliminated unused skills, kept idle MCPs out of context, and corrected misconfigured compaction strategies.

Comet said the Opik update extended beyond observability to reduce coding agent costs behind the scenes. In the release, the company cited a customer that reduced AI spend by millions annually, while describing “zero restrictions” on how developers used AI.

“Claude Code and Codex are genuinely transformational tools,” said Gideon Mendels, Co-founder and CEO of Comet. “But most engineering leaders have no idea how their developers have them configured – which MCPs are loaded, which model is running by default, whether any of it maps to real outcomes. Opik answers the questions every VP of Eng should be asking right now — and gives them the tools to do something about it.”

Provided by Globe Newswire on behalf of Comet. Click to read original content.