resume-dev-team

Resumes a crashed Claude Code dev-team session in a new Terminal tab using its recorded session ID.

1|Updated Jun 13, 2026
One-click install
npx skills add https://github.com/apireno/agent-workflow-template --skill resume-dev-team-apireno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: resume-dev-team
Source: https://github.com/apireno/agent-workflow-template/tree/main/.claude/skills/resume-dev-team
Command: npx skills add https://github.com/apireno/agent-workflow-template --skill resume-dev-team-apireno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When a per-repo dev-team session crashes mid-sprint, the orchestrating CTO session loses its worker and the sprint stalls. This Skill recovers the crashed session by reading the recorded session ID and relaunching it with claude --resume, avoiding a full restart and lost context. ## Core Features & Use Cases - Session Recovery: Reads the repo's .claude/current-session.id, verifies the matching JSONL transcript exists, and opens a new Terminal tab running claude --resume <session-id>. - Fleet-Aware Anchoring: Resolves the CTO home via multiple validated anchors (environment variables, .cto-path files, ~/.cto/home) and looks up the repo path in the .cto/projects.yaml registry. - State Cleanup: Clears the repo's CRASHED flag and re-applies the pinned model so the resumed session matches the original sprint configuration. - Use Case: /sprint-status reports repo api-service as CRASHED. Run this Skill with the repo name to relaunch its session in a new Terminal tab, then verify progress with /peek. ## Quick Start Ask the agent to resume the crashed dev-team session for a specific repo by name, for example: resume the dev team session for repo api-service.

Frequently Asked Questions about resume-dev-team

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I resume a crashed Claude Code session?▼

Run this Skill with the repo name as the argument. It reads the session ID from the repo's .claude/current-session.id file, verifies the JSONL transcript exists, and opens a new Terminal tab running claude --resume with that session ID.

How do I recover a dev-team session after a crash in a multi-repo setup?▼

Invoke the Skill with the crashed repo's name as registered in .cto/projects.yaml. It resolves the repo path from the fleet registry, relaunches the session, and clears the CRASHED flag so sprint monitoring resumes normally.

Why does session resume fail with 'no JSONL found'?▼

The recorded session ID has no matching transcript file under ~/.claude/projects, meaning the session was deleted or never persisted. The suggested recovery is to re-run /handoff for that repo to start a fresh session.

Does this work outside macOS Terminal?▼

No. The Skill spawns the resumed session via an osascript AppleScript that drives the macOS Terminal application. On other platforms or terminal emulators the tab-launch step will fail.

What happens if the repo is not in the fleet registry?▼

The Skill exits with an error stating the repo is not in .cto/projects.yaml. You must register the repo in the CTO home registry (via /setup) before its sessions can be resumed.