claude-rescue
Skill1 starsChanged 12 days agoApache-2.0View on GitHub
Delegate a task to Claude Code for investigation, planning, implementation, debugging, or testing when the user asks Claude to help or requests a second agent.
In this repository6 other files it gives its agents.
- claude-adversarial-reviewSkill
- claude-cancelSkill
- claude-resultSkill
- claude-reviewSkill
- claude-setupSkill
- claude-statusSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Read shared runtime instructions before invoking the companion.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
claude:rescue
Delegate the substantial work to Claude with a clear brief rather than solving it twice. Use the rescue command, normally with --background for substantial work. Monitor incremental status while this Codex task remains active, then retrieve and evaluate the result. Honor explicit model and effort choices; use --access read-only|edit|shell to match capabilities to the authorized task. When the user requests settings selection, obtain the missing choices before launching; reuse choices already supplied. Read the returned report and decide whether to accept, verify, or resume with specific feedback. Continue an authorized plan into implementation in the same session using --resume and explicit capability flags; preserve the exact job UUID and caller identity when available.
Read shared runtime instructions before invoking the companion. They define entrypoint resolution, task briefs, permissions, session continuation, and result handling.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

