GitHub · Go
bugyal/skeptic
Runs BOTH controls (nop + oracle) across EVERY task in a coding-agent benchmark, classifies the outcome, captures evidence, and lints leaks statically. One binary, zero LLM calls.
- Stars
- 5
- Forks
- 1
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: ai-agents, benchmarking, cli, developer-tools, golang, llm-evaluation, swe-bench, terminal-bench, testing
Latest data point: Nov 22, 2026 · 5 stars · 1 forks