kb-stats
Skill1 starsChanged 32 days agoMITView on GitHub
Use when the user asks for numbers about their own Claude Code or Codex usage — how many sessions, which projects, Claude vs Codex, models, outcomes, top topics, activity per day — answered from the sessions KB with `kb stats` and `kb sql`.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Before you write a custom query, read references/schema.md in this skill's folder: the tables and columns.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
kb-stats
Ready-made reports:
kb stats overview— sessions, turns, prompts (typed by the user; messages from other agents do not count) and date range per agentkb stats projects— top projectskb stats agents— sessions per agent and modelkb stats outcomes— done / partial / abandoned / questionkb stats tags— top summary tagskb stats daily— sessions and prompts per day, last 30 dayskb stats subagents— subagent transcripts per agentkb stats errors [--since 7d] [--project P]— tool errors that came back in 2 or more sessions, with the session and turn where each was first seen (kb show <short> --turn N)
Custom questions: kb sql "<SELECT …>" (read-only). Cells over 80 chars end with …; add --width 0 to see them whole.
Before you write a custom query, read references/schema.md in this skill's folder: the tables and columns.
Report the numbers exactly as returned and say which filters you used.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.