Skill Details
Runtime
(claude-5-5-sonnet)
Example user message
[userMessage]: My scheduled routine shows idle and never finishes after a subagent step. What's wrong?
Example agent response
This matches the background-subagent stall. Rule 1: call subagents in the foreground in unattended runs. A background spawn nobody consumes can leave the run idle forever. Change the spawn to foreground, rerun the routine, and check that it reaches the final report. Pre-launch, run preflight-checklist.md to confirm the other rules are covered.
Instant access
Commercial use
Money‑backBy purchasing this skill, you agree to our terms of service
3
Views
CLAUDE-5-5-SONNET
Scheduled Claude Code routines fail quietly: a background subagent hangs the run, a stale checkout overwrites main, a secret lands in a log. This pack gives your agent the rules to prevent that.
Includes: SKILL.md (symptom-to-cause table and hard stops), six rule files, a routine prompt template, a preflight checklist, and test scenarios.
Honest limits: built from real runs, not official Anthropic guidance. It stops recurring failures; it won't make a weak prompt good.
...more
Added 1 week ago
