// Recover Codex and Claude sessions from tmux cockpit panes, CX SAVE snapshots, codex-cockpit history, and recent Codex logs without overwriting the useful restore source first.
| name | codex-session-recovery |
| description | Recover Codex and Claude sessions from tmux cockpit panes, CX SAVE snapshots, codex-cockpit history, and recent Codex logs without overwriting the useful restore source first. |
| license | MIT |
| compatibility | Requires tmux and Vincent's tt helper with codex-cockpit snapshot support. |
| metadata | {"internal":true,"version":"0.1.0","spec":"agentskills-v1"} |
Recover crashed, detached, or confusing Codex/Claude tmux cockpit sessions while preserving the existing restore evidence. The priority is to find the right resume command or safe restore plan before writing new snapshots.
cx, or CX SAVE state.codex resume ... command for a pane.CX SAVE.tt codex-snapshot, tt autosave on, or tt doctor --fix until the candidate restore source is known.tt title "tmux recovery" when available.tt statustmux list-keys -T root MouseDown1StatusRight MouseDown3StatusRighttmux source-file ~/.tmux.conf.local and recheck.tt snapshot-history codex-cockpit 40.find ~/.local/state/tt/history/codex-cockpit -maxdepth 1 -type f -name '*.tsv' -print | sort | sed -n '1p;$p'tt restore-preview <snapshot>.tt codex-restore all <snapshot>.tt codex-restore pane <target> <snapshot>.tt codex-restore window <session:window> <snapshot>.--execute is present. Show the dry run before executing.--execute only after the user approves or the current request clearly asks to restore.~/.codex/sessions/YYYY/MM/DD/*.jsonl files.codex resume <id> command first. Skip the long method unless asked.cockpit:2.4 or %123.~/.local/state/tt/history/codex-cockpit/.codex resume ... or claude resume command when available.--execute.Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.
Maintain and release the crawlkit Go library, preserving downstream compatibility for gitcrawl, slacrawl, discrawl, and notcrawl.
Template skill for repository authors; excluded from public publishing.
Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the ghcrawl CLI.
Maintain, verify, and release graincrawl, the local-first Granola archive CLI, including SQLite archive behavior, read-only Granola source boundaries, Homebrew tap packaging, and crawlkit-powered TUI/snapshot surfaces.
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.