ops-resume

Featured

OPS on-demand: This skill should be used when the user asks to "resume sessions", "reopen ghostty…

AI & Automation 188 stars 22 forks Updated today MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
76
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# ops-resume Load `ops-rules` before acting. Public repo (no personal data). Outbound: one draft → one approval → one send. If `AskUserQuestion` / `Workflow` are missing, follow Rule 10 in `ops-rules` (Hermes: numbered options / two-turn Telegram card; `delegate_task`). Reopen recently-closed Claude Code sessions — **one session per Ghostty tab**. For every recent session transcript under `~/.claude/projects`, the helper opens a new Ghostty tab (`cmd+t`) and types `cd <cwd> && claude --resume <sessionId>`, so each session resumes in its own tab from whatever directory or repo it was running in. **Default:** every session touched in the **last 60 minutes**, from **any directory**. Platform: macOS + [Ghostty](https://ghostty.org) only. Tabs are driven via AppleScript System Events, so Accessibility permission must be granted to the terminal running this. ## How it works 1. Scans `~/.claude/projects/**/*.jsonl` and keeps files whose mtime is inside the lookback window (default 60 min) but older than `OPS_RESUME_MIN_AGE_SEC` (default 45s — so the session you are _currently_ in is not reopened). 2. Keeps only real interactive sessions (UUID filenames); skips subagent transcripts (`agent-*`), workflow journals, and empty/junk sessions. 3. Reads each session's original `cwd` from the transcript. 4. For each, opens a fresh Ghostty tab and resumes the session there. ## Usage Run the bundled helper. Pass through any flags the user gave (`$ARGUMENTS`). Always preview ...

Details

Author
Lifecycle-Innovations-Limited
Repository
Lifecycle-Innovations-Limited/claude-ops
Created
5 months ago
Last Updated
today
Language
Shell
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category