Menu
Analyze Claude Code session data from ~/.claude/projects/ to surface usage patterns, heavy sessions, and context-limit problems.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Draft a cold email that gets a reply from someone influential — an investor, founder, hiring manager, podcast host, or potential collaborator. Use whenever the user wants to reach out to someone they don't know personally.
Generate a large idea set with four parallel agents, then filter it down through two debate rounds. Use when the user wants to brainstorm or explore possibilities for a project, product, feature, or strategy.
Refine a rough SPEC.md into an implementation-ready specification through a multi-round interview, then break it into ordered tasks. Use when starting a new feature or turning a rough idea into something a developer can build without asking questions.
| name | session-stats |
| description | Analyze Claude Code session data from ~/.claude/projects/ to surface usage patterns, heavy sessions, and context-limit problems. |
Run the script next to this file and interpret what comes back:
python3 scripts/session_stats.py
When installed as a plugin the path is ${CLAUDE_PLUGIN_ROOT}/skills/session-stats/scripts/session_stats.py. It reads every .jsonl under ~/.claude/projects/, needs no arguments, and works on any machine — it resolves the home directory itself.
The one thing that trips people up: total tokens is dominated by cache reads, which are re-counted on every assistant turn. A session showing hundreds of millions of "tokens" was not billed at that scale and did not process that much unique text — it means a large context was re-read many times. Output tokens and message count are the honest measures of how much work a session actually did; the total is best used as a relative signal of context weight, comparing sessions against each other rather than against an absolute number.
With that in mind, give the user a real read of their data rather than a restatement of the table:
Then suggest fixes that follow from what you actually saw. Sessions that balloon in context usually want /clear at natural task boundaries or /compact before auto-compaction fires. Heavy cache-creation relative to peers points at a large always-loaded CLAUDE.md. Many tool calls per session points at verbose operations worth delegating to subagents. Very long single sessions are usually less effective than several focused ones — say so when the data shows it, and skip it when it doesn't.