Sign inGet started
–

Runs a single Terminal-Bench task through a bounded, board-gated loop of smoke runs, diagnosis, and approved fixes until the task passes.

Lift · GLM-5.3-flash+25ppdirectional · all models →
87
Trustsecurity · quality · license · upkeep
Scan Saferisk 0/100
LicenseMITserved via MCP

Use via SkillzBench MCP

One MCP for your whole loadout — create a key in your dashboard, then:

claude mcp add --transport http \\\n  skillzbench https://mcp.skillzbench.com/mcp \\\n  --header 'Authorization: Bearer sb_live_XXXX'

Direct from source

https://github.com/paperclipai/paperclip/tree/HEAD/.agents/skills/terminal-bench-loop

Pinned here at HEAD:18f05fee5f80… — only scanned versions are ever served.