Mouse is an open source harness for long-running coding agents built on OpenCode. It passed 25 of 30 tasks on FrontierHarness Eval using Kimi K3, enforcing completion loops with verification rules to improve task completion accuracy.
Mouse coding agent achieved 23 of 30 passes on FrontierHarness tasks using GLM-5.3-Flash at $0.29 per pass, performing comparably to other agents on the full GLM-5.3 model while using significantly cheaper inference. Mouse missed two tasks that Kimi K3 passed on DeepSWE benchmarks but matched K3's performance on other shared failures.
Mouse, built on OpenCode, achieved first place on the FrontierHarness benchmark with a score of 25/30, up from OpenCode's last-place 15/30. The key improvement was a verification loop that enforces a fixed sequence of deterministic steps—checking git changes, running repo checks, verifying no tests were deleted, and validating a MOUSE_AUDIT file—allowing the agent to iteratively refine solutions until all requirements pass, achieving an impressive 90.6% cache hit rate.
FrontierHarness v1.0 evaluated 12 configurations of software development and terminal-based task harnesses using the Kimi K3 model across 360 trials. Claude Code achieved a 63% pass rate but cost 5.6× more per successful task than DSH Creator, which matched its pass rate, demonstrating that efficiency and task completion are separate skills across harnesses ranging from $1.05 to $18.34 per task.