What it does
It uses the SubagentStart and SubagentStop lifecycle hooks. Each time Claude spawns or finishes a subagent, a JSON entry is appended to .claude/agent-log.jsonl, recording the agent name, the event type and an ISO timestamp.
It suits debugging multi-agent workflows, checking which agents ran and in what order, and estimating AI usage per session.
The log is kept offline and has no dependencies, so it does not rely on external services.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 111
subagent-lifecycle-logger
Audit trail for subagent invocations using SubagentStart and SubagentStop lifecycle hooks. Every time Claude spawns or finishes a subagent, a timestamped JSON entry is appended to .claude/agent-log.jsonl — recording the agent name, event type, and ISO timestamp. Provides an offline, zero-dependency log for debugging multi-agent workflows, tracking which agents ran and in what order, and estimating AI usage per session.
As shown on www.aitmpl.com when we last read it