From trantor
Write a rich handoff for the CURRENT session so a fresh Claude Code session can take over with a full new context window (instead of compacting). Use proactively when context is getting full, or before ending, to pass the baton cleanly. Trigger: /trantor:handoff
How this skill is triggered — by the user, by Claude, or both
Slash command
/trantor:handoffThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Write a complete handoff capturing everything a NEW session needs to continue this work without
Write a complete handoff capturing everything a NEW session needs to continue this work without re-deriving context, and save it so the next session in this project auto-loads it on start.
Compose a thorough markdown handoff for the current task with these sections (be specific — exact file paths, concrete next actions; the successor has a fresh window and only this):
Save it by piping the markdown to the helper:
cat << 'HANDOFF' | node "$(dirname "$(command -v claude)")/../<plugin>/bin/write-handoff.mjs"
<your handoff markdown>
HANDOFF
(Or call the plugin's bin/write-handoff.mjs directly via its ${CLAUDE_PLUGIN_ROOT}.)
Tell the user: open a fresh terminal + claude in this same project directory — the
SessionStart hook will detect the handoff and the new session takes over with a full window.
(The PreCompact hook also writes one automatically at the compaction threshold.)
npx claudepluginhub sashabogi/trantor --plugin trantorProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.