Touchstone
← Harnesses

repo_agent

legacycurrent

The agentic loop — explore the repo, make surgical edits, run the failing test, iterate.

why it exists: The core strategy every localharness version builds on (grep / ranged+full read / surgical edit).

Models
0
have run it
Solved
0
gauntlet benches

Models on this harness (gauntlet solved / attempted)

ModelSolvedBy domain

No runs recorded on this harness yet.