More screenshots

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Claude Routine Guard

    2

    Rules, prompt template and preflight checklist that stop scheduled Claude Code routines from stalling, clobbering main, or leaking secrets.

    $11.99

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    Security scanned
    Claude Routine Guard

    Claude Routine Guard

    Example session with this skill installed

    My scheduled routine shows idle and never finishes after a subagent step. Review my routine prompt with claude-routine-guard.

    • Read your context and instructions
    • Compiled the claude routine guard
    • Generated the document

    Summary

    Your routine stalled after a subagent step. This is the background-subagent pattern from Rule 1, so the fix is to call subagents in the foreground.

    SymptomLikely causeRule
    Run shows idle and never finishes after a subagent stepA background spawn that nobody consumes1

    What to change

    1. Find every subagent call in the routine prompt.
    2. Set each one to run in the foreground, so the run waits for its result.
    3. Make sure the final report is the last step, and that it gets written after the subagent returns.
    Call each subagent in the foreground and wait for its result before the next step.
Do not spawn background agents in an unattended run.

    claude-routine-guard.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    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.

    What's included:

    • SKILL.md: triggers when you write or debug a routine, with a symptom-to-cause table and hard stops
    • Six rule files: foreground subagents, reset before edit, commit and push, egress and secrets, one consolidated report, parallel agents in worktrees
    • A fill-in routine prompt template with the rules built in
    • A pass/fail preflight checklist
    • Scripted test scenarios with expected answers

    Honest limits: built from real runs, not official Anthropic guidance. It stops recurring failures; it won't make a weak prompt good.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 2 days ago

    • Passed all security checks, Safe to install

    Listed2 days ago

    What's inside

    Frequently Asked Questions