From ccgraft
Import a ccgraft session export into Claude Code. Validates manifest, regenerates UUIDs, and imports session data with pre-import snapshots for recovery.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ccgraft:import-sessionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The argument is the path to a `.claude-sessions/<name>/` export directory (containing `.ccgraft-manifest.json`).
The argument is the path to a .claude-sessions/<name>/ export directory (containing .ccgraft-manifest.json).
If the user provided an export path, run:
bash "${CLAUDE_PLUGIN_ROOT}/bin/ccgraft-import" $ARGUMENTS
If no path was provided, show available exports in the current project:
ls -la .claude-sessions/ 2>/dev/null || echo "No exports found in this directory. Run /ccgraft:export-session in the source project first, then provide the path here."
After import, tell the user: To continue the imported session, run claude --continue in a new terminal.
Note: The import runs in the current directory by default. If the user needs to import into a different project, they can pass --target-project <path>.
npx claudepluginhub achxy/dotclaude --plugin ccgraftBrowse shared Claude Code sessions from another user via LAN or relay, select one, decrypt with passphrase, and install locally as JSONL conversation history.
Browses, inspects, and imports Claude Code session history. Lists sessions by project/tool/date, shows details or full conversations, imports to markdown journals.
Exports Claude Code session JSONL files to human-readable markdown with role markers and timestamps. Use to save, review, share transcripts, or feed dev-diary pipelines.