Standing rules that keep an autonomous AI research agent honest: reward hacking, fabricated results after a failed run, data leakage, undertuned baselines, single-seed claims, LLM-judge bias, premature done. An Agent Skill for Claude Code, Codex, and Cursor.
Cross-referenced across 55 tracked directories
#9049
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
7/27/2026
Created
1
GitHub Stars
5
Open Issues
8/9/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
dprctd
Detect duplicated code, dead code, and anti-patterns in AI-generated codebases
tomquirk
A multi-model council plugin for OpenCode that runs prompts across multiple LLMs and synthesizes their responses to identify consensus and discrepancies.
...more