Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Schedule After Usage Reset

BSecurity

Schedule a task to run after the Claude usage limit resets. Use when the user says things like: schedule this after my usage resets, run this when my tokens refresh, queue this task for after the limit lifts, or any variation of wanting to defer a task until after a Claude usage/token limit reset. Finds the reset time from the Anthropic usage API and calls /schedule with that exact time. Trigger with phrases like \"schedule after my usage resets\" or \"run this when my limit lifts\".

2,785 stars
0 votes
0 copies
1 views
Added 9/24/2026
ai-agentspythonbashexpressgitapisecurity

Works with

claude codeapi

Security Analysis

B75/100
criticalAccesses system keychains or credential stores
criticalSends environment variables or credentials to an external URL

Pro shows the line behind each finding and how to fix it

Scanned 9/24/2026

$npx -y skills add jeremylongshore/claude-code-plugins-plus --skill schedule-after-usage-reset --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Schedule After Usage Reset?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Schedule After Usage Reset
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/jeremylongshore-schedule-after-usage-reset-fc0d12c0/badge)](https://www.skillsdirectory.com/skills/jeremylongshore-schedule-after-usage-reset-fc0d12c0)

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

Download with Pro
Files
SKILL.md
---
name: schedule-after-usage-reset
description: "Schedule a task to run after the Claude usage limit resets. Use when the user says things like: schedule this after my usage resets, run this when my tokens refresh, queue this task for after the limit lifts, or any variation of wanting to defer a task until after a Claude usage/token limit reset. Finds the reset time from the Anthropic usage API and calls /schedule with that exact time. Trigger with phrases like \"schedule after my usage resets\" or \"run this when my limit lifts\"."
allowed-tools: Bash(security:*), Bash(curl:*), Bash(python3:*), Bash(date:*)
version: "1.0.0"
author: patricksong1993 (https://github.com/patricksong1993)
license: MIT
compatibility: Designed for Claude Code
tags: [scheduling, rate-limit, automation, claude-code]
---

# Schedule After Usage Reset

Automatically find the usage reset time and call `/schedule` with it. No questions asked.

## Overview

When the user wants to defer a task until after their Claude usage/token limit
resets, this skill removes the manual step of looking up the reset time. It reads
the reset timestamp from the Anthropic usage API, converts it to the user's local
timezone, adds a small buffer, and hands the task off to the `/schedule` skill at
that exact time. The user never has to figure out *when* the limit lifts — they
just say what they want run.

## Prerequisites

- Running inside Claude Code with a valid OAuth credential stored under the
  `Claude Code-credentials` keychain entry (read via `/usr/bin/security`).
- Network access to `https://api.anthropic.com` to query the usage endpoint.
- `python3` available on `PATH` (used to parse the JSON token and API response).
- The `schedule` skill installed — this skill defers the actual scheduling to it.

## Instructions

### 1. Get the reset time

Fetch from the Anthropic usage API:

```bash
token_json=$(/usr/bin/security find-generic-password -s 'Claude Code-credentials' -w 2>/dev/null)
access_token=$(echo "$token_json" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('claudeAiOauth',{}).get('accessToken',''))")
curl -s -H "Authorization: Bearer $access_token" \
     -H "anthropic-beta: oauth-2025-04-20" \
     -H "User-Agent: claude-code/2.1" \
     "https://api.anthropic.com/api/oauth/usage"
```

Parse `five_hour.resets_at` (or `seven_day.resets_at`). Convert UTC → user's local
timezone. Add 5 minutes as buffer.

### 2. Get the task

If not provided as an argument, ask: "What should I run after the reset?"

### 3. Call /schedule

Invoke the `schedule` skill, passing the task and the reset time + 5min buffer:

```
/schedule "<task>" at <HH:MM> <timezone>
```

The `schedule` skill handles everything from there — just like calling it directly.

## Output

- A `/schedule` invocation has been created for the user's task at the reset time
  plus the 5-minute buffer, expressed in the user's local timezone.
- A short confirmation of what was queued and when it will run (for example:
  "Queued `<task>` to run at 14:35 America/New_York, just after your usage resets").
- The `/schedule` skill owns execution from that point — this skill's job ends once
  the handoff has been made.

## Error Handling

- **Rate limited (HTTP 429):** wait 15 seconds and retry the usage request once.
- **Still failing after the retry:** ask the user for the reset time directly and
  proceed with `/schedule` using their answer.
- **Missing or empty access token:** the keychain lookup returned nothing — ask the
  user for the reset time rather than guessing.

## Examples

**Defer a build until the limit lifts**

```
User: schedule a full test run for after my usage resets
→ Read five_hour.resets_at from the usage API (e.g. 19:30 UTC)
→ Convert to local time and add 5 min → 14:35 America/New_York
→ /schedule "run the full test suite" at 14:35 America/New_York
```

**Reset time unavailable**

```
User: queue this report for when my tokens refresh
→ Usage API still 429 after one retry
→ Ask: "What time does your usage reset?" → user says 3:00 PM
→ /schedule "<task>" at 15:05 <timezone>
```

## Resources

- Anthropic usage endpoint: `https://api.anthropic.com/api/oauth/usage`
  (`five_hour.resets_at` / `seven_day.resets_at` carry the reset timestamps).
- The `schedule` skill — this skill is a thin front-end that resolves the reset
  time and then defers all scheduling to it.

Attribution

jeremylongshorejeremylongshore
View sourceSee grades on GitHubMore from jeremylongshore →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →