Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -36% | 0% |
Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.
Steps:
tail -1 ~/.claude/history.jsonl | jq -r '[.sessionId, .project] | @tsv'find ~/.claude -name "half-clone-conversation.sh" 2>/dev/null | sort -V | tail -1<script-path> --preview <session-id> <project-path><script-path> <session-id> <project-path>New session: <id> line). Give the user the exact command to resume it directly, no picker needed: claude --resume <new-session-id> The script automatically appends a reference to the original conversation at the end of the cloned file. (The new session is also marked [HALF-CLONE <timestamp>], e.g. [HALF-CLONE Jan 7 14:30], so claude -r and picking it works as a fallback.)
Other measured skills in the registry, with their headline benchmark lift.