by boshu2 · Claude Skill · ★ 449
AgentOps AgentOps is the operating loop a coding agent follows: one intent, one bounded build, one fresh judge, then report and stop. It also ships skills to orchestrate multi-agent systems. For contested calls, opt into (independent judges) or duel mode (sealed perspectives before Plan). Quickstart One command installs the corpus into every coding agent you use. The loop runs as skills inside your coding agent (Claude Code, Codex, Cursor, …): type in that agent's chat, or ask for , , , and by name. No other runtime is required.
| Stars | 449 |
| Forks | 41 |
| Language | Go |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 39/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-15 |
| Created | 2025-11-05 |
| Platforms | claude-code, codex, go |
| Est. Tokens | ~7600k |
These tools work well together with agentops for enhanced workflows:
Explore other popular claude skill tools:
agentops is DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it.. It is categorized as a Claude Skill with 449 GitHub stars.
agentops is primarily written in Go. It covers topics such as ai-agents, claude, claude-code.
You can find installation instructions and usage details in the agentops GitHub repository at github.com/boshu2/agentops. The project has 449 stars and 41 forks, indicating an active community.
agentops is released under the Apache-2.0 license, making it free to use and modify according to the license terms.