Skip to content
Back to skills

Claude Sessions

ASecurity

Inspect and manage Claude Code background sessions from Codex. Use for repository-scoped status, recent logs, best-effort results, stopping, respawning, removing, or attaching to a known Claude background job.

  • 8 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
ai-agentsnode

Works with

  • claude code
  • terminal

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 24, 2026

npx -y skills add sanchitmonga22/cc-for-codex --skill claude-sessions --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claude Sessions?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Claude Sessions
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sanchitmonga22-claude-sessions/badge)](https://www.skillsdirectory.com/skills/sanchitmonga22-claude-sessions)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: claude-sessions
description: "Inspect and manage Claude Code background sessions from Codex. Use for repository-scoped status, recent logs, best-effort results, stopping, respawning, removing, or attaching to a known Claude background job."
---

# Claude Sessions

Use the executable bridge launcher at the sibling skill path `../claude-code/scripts/cc-for-codex`, resolved to an absolute path. Invoke it directly, never through a bare `node` lookup.

## Safe operations

- `status --all`: list sanitized jobs scoped to the canonical working directory.
- `logs <id>`: show recent terminal output.
- `result <id>`: alias to recent logs; Claude has no dedicated structured result subcommand.

## State-changing operations

Resolve the exact 8-hex ID with `status --all` immediately before acting.

- Stop: `stop <id> --confirm-stop stop:<id>`. This preserves the conversation.
- Respawn: `respawn <id> --confirm-respawn respawn:<id>`. Warn that usage can resume.
- Remove: only for `done`, `failed`, or `stopped`; use `remove <id> --confirm-remove remove:<id>`. Removal can delete a safely removable Claude-created worktree. Never retry with `--discard-unpushed`.
- Attach: requires a real TTY. Open it in the Codex terminal; do not treat Ctrl-C as a request to stop the background session.

Never act on an ID outside the current repository scope. Never use `respawn --all`, daemon-wide stop, or global cleanup through this skill.

Read [references/lifecycle.md](references/lifecycle.md) for state semantics and resume behavior.

Files in this skill

  • SKILL.md1.5 KB
  • agents/openai.yaml204 B
  • references/lifecycle.md880 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…