Back to all repositories
LI
harnessloop
by litianyi-007
让长时间运行的 AI agent 任务变得可审计的协议——轮次、scope-lock、证据契约、runtime 验收 eval。拒绝自相矛盾；并如实登记它强制不了什么。 · An auditability protocol for long-running AI agent tasks — rounds, scope-lock, evidence contracts, runtime acceptance evals. Refuses self-contradiction; states plainly what it cannot enforce.
0stars0forks0watchers/subscribers0issues
agent-protocolai-agentsauditabilityclaude-codeclaude-code-pluginevaluationllm-tooling
- Language
- Python
- License
- MIT License
- Size
- 3.8 MB
- Created
- Jun 28, 2026
- Last Updated
- Aug 12, 2026
- Last Pushed
- Aug 3, 2026
Available Plugins
Loading plugins...
Evaluate before installing
- Review the source repository, recent maintenance, and license on GitHub.
- Read the marketplace manifest and plugin source files before running commands.
- Start with the smallest required permission set and validate behavior in a safe environment.