by roy-tong · MCP Server · ★ 217
AgentMeasure Find repeated failures and retries in your Codex sessions, with local evidence. Healthcheck reads existing Codex Desktop rollout logs and produces a terminal summary and a local HTML report. It checks duplicate records, retry chains, and consecutive tool failures. Missing evidence is UNPROVABLE, never silently zero. Analysis runs locally with no runtime network calls. Engineering preview: Codex CLI is not yet independently verified; Claude Code is not supported yet. The Git install above is available now; PyPI publishing is being prepared.
| Stars | 217 |
| Forks | 9 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 40.75/100 |
| Open Issues | 10 |
| Last Updated | 2026-10-22 |
| Created | 2026-08-16 |
| Platforms | mcp, python |
| Est. Tokens | ~118k |
These tools work well together with AgentMeasure for enhanced workflows:
Explore other popular mcp server tools:
AgentMeasure is Inspect Codex / Claude logs, verify metering samples and re-count supported billing exports. Free local tools; bounded $10 diagnosis and $20 QA.. It is categorized as a MCP Server with 217 GitHub stars.
AgentMeasure is primarily written in Python. It covers topics such as agent-commerce, agent-economy, agent-evaluation.
You can find installation instructions and usage details in the AgentMeasure GitHub repository at github.com/roy-tong/AgentMeasure. The project has 217 stars and 9 forks, indicating an active community.
AgentMeasure is released under the MIT license, making it free to use and modify according to the license terms.