Compressed browser snapshots cut agent token use sharply
Opera's tooling team compared four ways to send browser page information to an AI agent. The test used 7 browser tasks adapted from AXI's bench-browser suite, with 5 runs for each condition. The model was gpt-5.5 medium reasoning.
All four formats reached a 100% pass rate. The average were very different: unprocessed chrome-devtools-mcp used 179.2k, the AXI reference CLI used 102.2k, Opera's raw output without used 107.5k, and Opera's compressed opera-compact format used 36.3k. Average tool calls were also lowest with opera-compact at 1.4.
The removed repeated or unnecessary page details, including that were already implied by a role, repeated text nodes, and repeated URLs replaced by a . The tools ship as opera-browser-cli and opera-devtools-mcp under the .
Key points
- All four browser snapshot formats had the same 100% pass rate.
- opera-compact used 36.3k average , far below 179.2k for unprocessed chrome-devtools-mcp.
- The compressed format removes repeated URLs, repeated text, and unnecessary .
- opera-compact also had the lowest average tool calls at 1.4.
- The tools are released as opera-browser-cli and opera-devtools-mcp with an .