Skills runlater
๐Ÿ“ฆ

runlater

Content revision r1 Safe โš™๏ธ External commands

Schedule HTTP Requests with RunLater

Hosting limits can make scheduled HTTP tasks difficult to manage. This skill guides connected RunLater MCP tools to schedule requests, manage jobs, and inspect failures.

Supports: Claude Codex Code(CC)
Maintain this Skill? Claim it ๐Ÿ“Š 73 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "runlater" from https://skillstore.io/skills/runlater-app-runlater.md and its manifest at https://skillstore.io/api/skills/runlater-app-runlater/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "runlater". Schedule a request at 9am tomorrow, but I have not provided a timezone.

Expected outcome:

Which IANA timezone should I use for 9am, such as America/Chicago?

Using "runlater". Schedule a GET request to my localhost endpoint.

Expected outcome:

RunLater requires a public URL and refuses local addresses. Provide a deployed endpoint or an authorized public tunnel URL.

Using "runlater". Test my scheduled webhook that creates an order.

Expected outcome:

Running this webhook now will send a real request and may create an order. Do you approve this immediate test?

Security Audit

Safe
v1 โ€ข 11/17/2026 Open versioned report

All 13 static findings are false positives caused by Markdown inline code, not Ruby or shell execution. No evidence found of prompt injection, credential exfiltration, or unauthorized actions in SKILL.md. This review covers the instructions only, not the external MCP service implementation.

1
Files scanned
37
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/runlater-app-runlater/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/runlater-app-runlater/security.svg)](https://skillstore.io/skills/runlater-app-runlater?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/runlater-app-runlater?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/runlater-app-runlater/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/runlater-app-runlater.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA ยท BibTeX ยท CFF)

APA citation

runlater-app. (2026). runlater security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/runlater-app-runlater/audits/1

BibTeX citation

@techreport{runlater-app-runlater-app-runlater-2026, author = {runlater-app}, title = {runlater security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/runlater-app-runlater/audits/1}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "runlater security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "runlater-app" date-released: "2026-11-17" url: "https://skillstore.io/skills/runlater-app-runlater/audits/1" identifiers: - type: other value: "skillstore:runlater-app-runlater:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
65
Maintainability
87
Content
65
Community
74
Spec Compliance

What You Can Build

Schedule application maintenance

Schedule a public maintenance endpoint when hosting cron limits do not meet the required frequency.

Investigate failed scheduled requests

Inspect recent response previews, status codes, and durations, then pause a failing schedule while investigating.

Arrange a one-time webhook

Schedule an authorized webhook for a specific time and confirm the timezone and next execution time.

Try These Prompts

View scheduled jobs
List my RunLater schedules and show my account plan, limits, and usage.
Schedule one public request
Schedule a GET to [public URL] on [date] at [time] in [IANA timezone]. Confirm the next run time.
Create a recurring webhook
Schedule a POST to [public URL] with [cron expression] in [IANA timezone]. Use my authorized authentication header. Ask before testing it.
Investigate and control a failing job
Inspect recent runs for [schedule ID]. Summarize status codes, durations, and response previews. Pause it if failures persist. Ask before running it immediately.

Best Practices

  • Specify an IANA timezone and verify the next run time returned by RunLater.
  • Use headers for endpoint secrets and verify the destination before sharing credentials.
  • Confirm immediate tests with side effects and inspect execution results before relying on a schedule.

Avoid

  • Scheduling an ambiguous local time without confirming the timezone.
  • Running a state-changing request without agreement or deleting a schedule without confirmation.
  • Using non-idempotent endpoints without considering retries after responses outside the 2xx range.

Frequently Asked Questions

What must be connected before using this skill?
The RunLater MCP tools must be available. This skill provides instructions, not the service implementation.
Which HTTP methods are supported?
The documented tools support GET, POST, PUT, PATCH, and DELETE requests.
Can I schedule requests to localhost?
No. RunLater requires public URLs and refuses private and local addresses.
How often can a recurring request run?
Cron schedules run at most once per minute. Use an IANA timezone to specify the intended local time.
How are authentication secrets supplied?
Pass endpoint secrets as headers. The instructions state that tools return header names, not values; the external implementation was not reviewed.
What happens when a scheduled request fails?
Responses outside the 2xx range count as failures and are retried. Inspect recent runs for status codes, durations, and response previews.

Developer Details

License

Unknown

Skillstore revision

r1

Version notice

The author did not declare a version.

Ref

75bf5843922e35c0edcbd8bd5f85db16fb540c72

Maintenance freshness

11/17/2026

Usage

0 downloads ยท 0 views

File structure

๐Ÿ“„ SKILL.md

View all