Drop a timeline marker into the current session for later A/B comparison.
/marker "<label>"
/marker "starting refactor"
What you’ll see: marker recorded: starting refactor — the marker is attached to the current session’s timeline. If the Arth engine isn’t reachable, you’ll see marker queued (engine unreachable): starting refactor instead and the marker is saved locally.
/marker "starting refactor" # annotate the start of an experiment arm
/marker "baseline recorded" # mark the comparison point
/marker "bug repro confirmed" # pin the moment a hypothesis was verified
{label, timestamp_ns, session_id} to the Arth engine’s markers API./tmp/claude-agents-otel/<session>/markers.jsonl) instead — markers are never lost, and the skill never blocks your session.Each invocation appends a new marker — running the same label twice records two distinct markers, so you can mark repeated checkpoints (e.g. each retry of an experiment) without overwriting earlier ones. The whole operation is inline shell with no agent spawns, so it adds effectively zero cost or latency to your session.
/tmp/claude-agents-otel/<session>/markers.jsonl when the engine is unreachable (append-only)| Problem | Fix |
|---|---|
no active session — run inside Claude Code |
The skill needs a live session ID; invoke /marker from within a Claude Code session |
usage: /marker "<label>" |
A label is required — quote it if it contains spaces |
marker queued (engine unreachable): <label> |
The Arth engine isn’t responding; the marker was saved locally. Check the engine is running (default http://localhost:3333, override with ARTH_BASE_URL) |