Help us improve
Share bugs, ideas, or general feedback.
From logbook
Generates monthly and yearly markdown reports analyzing message counts per project/branch from Claude Code session logs, separating human-typed from automated messages. Activates for usage statistics queries.
npx claudepluginhub florianbuetow/claude-code --plugin logbookHow this skill is triggered — by the user, by Claude, or both
Slash command
/logbook:messagesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate message-count reports from Claude Code session logs. Groups branches under their parent project. Separates human-typed messages from automated user turns (tool results, hooks).
Generates standup summaries of recent Claude Code sessions: lists done commits by project/branch/duration, in-progress tasks, and metrics like total time/sessions.
Converts Claude Code JSONL conversation logs to Markdown for retrospectives, with incremental/full/project-specific options, index summaries, and analysis templates like growth tracking and bug patterns.
Guides technical evaluation of code review feedback: read fully, restate for understanding, verify against codebase, respond with reasoning or pushback before implementing.
Share bugs, ideas, or general feedback.
Generate message-count reports from Claude Code session logs. Groups branches under their parent project. Separates human-typed messages from automated user turns (tool results, hooks).
python3 plugins/logbook/scripts/logbook.py messages --out docs/reports
This generates:
YYYYMM-logbook-messages.mdYYYY-logbook-messages.mdTo limit to a specific period:
python3 plugins/logbook/scripts/logbook.py messages --year 2026 --month 3 --out docs/reports
For preview only (no files written):
python3 plugins/logbook/scripts/logbook.py messages --preview
After running the script, display the top 10 table from stdout directly to the user. This is the inline preview — do NOT hide it behind a file path.
Show the user which report files were created and their paths.
Each report contains:
The reports show "You" (human-typed) and "Agent" counts for clarity.