Stats
Actions
Tags
From saferun-guard
Show the SafeRun Guard audit log — what actions the agent executed in recent sessions
How this skill is triggered — by the user, by Claude, or both
Slash command
/saferun-guard:logThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read the audit log file at `~/.saferun/audit.jsonl`. Each line is a JSON record of a tool action that was allowed and executed.
Read the audit log file at ~/.saferun/audit.jsonl. Each line is a JSON record of a tool action that was allowed and executed.
Fields: ts (timestamp), session (session ID), tool (Bash/Write/Edit/Read), input (command or file path), cwd (working directory).
Show the most recent 20 entries by default. If the user asks for more, show more.
Format as a readable table or summary. Group by session if there are multiple sessions.
If the file doesn't exist, tell the user no actions have been logged yet.
npx claudepluginhub cocabadger/saferun-guard --plugin saferun-guardDisplays audit logs for Claude Code components (skills, commands, agents, hooks) from .claude/audit/ to monitor health, identify stale items, and track coverage.
Inspects and queries Claude Code hook event logs from .claude/logs JSONL files. Subcommands list sessions, timelines, tool traces, agent lifecycles, team activity, stats, coverage, and daily summaries.
Implements session-aware structured JSONL logging for audit trails, usage analytics, cost tracking, and operation history in Python services.