AI Agents Metrics — AI skill for Claude Code

ai-agents-metrics

[](https://github.com/sg4tech/ai-agents-metrics/actions/workflows/ci.yml) [](https://pypi.org/project/ai-agents-metrics/) [](https://pypi.org/project/ai-agents-metrics/) [](https://github.com/sg4tech/ai-agents-metrics/blob/main/LICENSE) [](https://pypi.org/project/ai-agents-metrics/)

**Analyze your AI agent work history. Track spending. Optimize your workflow.**

AI is writing more of your code. You still don't know:

• How many sessions each thread contains
• Where the process breaks down and why
• Whether your workflow is getting faster or generating more rework

`ai-agents-metrics` extracts these signals from your existing Claude Code or Codex history. Point it at your history files and see what's happening: sessions per thread, token cost, and session timeline.

**Running this on 6 months of Claude Code + Codex history (3.85B tokens, 160 threads) surfaced:**

• 100% of Claude "retries" are subagent spawns, not user retries — attempt_count > 1 is structural, not a failure signal (F-001)
• Subagent delegation halves main-session tokens within-thread — median 2.05× compression, p = 0.000456 (F-007)
• Per-skill compression ranking — Explore 2.63×, code-reviewer 3.25×, commit 0.72× (F-008)

Full index: [docs/findings/](docs/findings/README.md). N=1 developer; the mechanisms generalize because they come from the tools, not the data.

---

Quick start

pipx install ai-agents-metrics

ai-agents-metrics history-upda