New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Deferred Task Execution

by sammcj in sammcj/agentic-coding

Delays execution of a task until a specified time or after a duration.

Apache-2.0Auto-check: notes

Install Deferred Task Execution

skills CLI
$ npx skills add sammcj/agentic-coding --skill deferred-task-execution -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sammcj/agentic-coding deferred-task-execution --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sammcj/agentic-coding.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Skills/deferred-task-execution .claude/skills/deferred-task-execution && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deferred-task-execution
GitHub stars
162
Token cost
~642 tokens
SKILL.md length
323 words
Files
2 (incl. scripts)
Skills in repo
62
Repo updated
First seen
Licence
Apache-2.0

At a glance

Delays execution of a task until a specified time or after a duration.

  • Works in 4 steps: Confirm the user's intent → Launch the timer in background → Wait for the timer → …
  • The user asks to run something later
  • SKILL.md covers Script Location, Supported Input Formats, Workflow and Important Notes
  • Runs Shell scripts from its folder

What it does

Deferred Task Execution is an agent skill from sammcj/agentic-coding. Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.

Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/wait-until.sh`).

The repository describes itself as: Agentic Coding Rules, Templates etc... The licence is Apache-2.0.

When your agent uses it

  • The user asks to run something later
  • In X minutes/hours
  • At a specific time
  • Schedule a command

Example prompts

  • “Use the deferred-task-execution skill to delay execution of a task until a specified time or after a duration”
  • “/deferred-task-execution”

Requirements

  • A Bash shell
  • Pre-approved tools (allowed-tools): Bash, Read, TaskStop

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Confirm the user's intent
  2. Launch the timer in background
  3. Wait for the timer
  4. Execute the deferred task

What it can do on your machine

Read from SKILL.md and the folder at commit 62ba5a2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • TaskStop

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deferred Task Execution loads about 642 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 323 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~642

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, TaskStop

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from sammcj/agentic-coding at commit 62ba5a2, republished under its Apache-2.0 licence (© sammcj). 323 words, ~642 tokens.

Download SKILL.mdSave it as .claude/skills/deferred-task-execution/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
deferred-task-execution
description
Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.
allowed-tools
Bash, Read, TaskStop

Deferred Task Execution

Delays agent work until a user-specified time using a background timer script, then proceeds with the deferred task.

Script Location

~/.claude/skills/deferred-task-execution/scripts/wait-until.sh

Supported Input Formats

The script accepts one argument in either format:

Duration - relative delay from now:

  • 30s, 5m, 1h, 90m, 2h30m, 1h15m30s

Clock time - specific time of day:

  • 14:30, 9:00, 3pm, 3:30pm
  • If the time has already passed today, it waits until that time tomorrow

Workflow

Step 1: Confirm the user's intent

Confirm what task to perform and when. Parse their natural language into a wait-until argument:

User saysArgument
"in 30 minutes"30m
"in an hour"1h
"in 2 and a half hours"2h30m
"at 3pm"3pm
"at 14:30"14:30
"at half past 9"9:30am

The script self-handles timezone via the USER_TZ variable defined at the top of wait-until.sh (defaults to Australia/Melbourne). Clock-time arguments are interpreted in that zone regardless of host TZ. Don't ask the user about timezones unless they mention travelling.

Tell the user exactly what will happen and when the timer will fire. Ask them to confirm before starting.

Step 2: Launch the timer in background

Run the wait script using Bash with run_in_background: true:

~/.claude/skills/deferred-task-execution/scripts/wait-until.sh <argument>

Note the task ID from the response -- you need it to cancel.

Step 3: Wait for the timer

Background Bash notifies you when the script exits. Wait for that notification; don't poll.

Step 4: Execute the deferred task

Once the output contains "Timer complete. Proceed with deferred task.", carry out whatever work the user requested.

Important Notes

  • The agent session must remain open for the timer to work. If the user closes the session, the deferred task will not execute. Warn the user about this.
  • For very long waits (multiple hours), remind the user that the session needs to stay active.
  • If the user asks to cancel, use TaskStop with the background task ID.
  • Always tell the user the calculated wake time so they know when to expect the action.

© sammcj, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in Skills/deferred-task-execution of sammcj/agentic-coding.

  • SKILL.md
  • scripts/wait-until.sh

Open the folder on GitHubat commit 62ba5a2

Compare with similar skills

Deferred Task Execution next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deferred Task Execution compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deferred Task Execution this skillsammcj/agentic-coding162—~642Automated safety check: NotesApache-2.0
Defer Asyncthedaviddias/Front-End-Checklist74k—~494Automated safety check: PassMIT
SpecifyZaxbyHub/opencode-swarm490—~2.8kAutomated safety check: PassMIT
Delay Claim Lettermohitagw15856/pm-claude-skills1.4k—~1.6kAutomated safety check: PassMIT
Specifyteam-attention/hoyeon173—~7kAutomated safety check: PassMIT
Speckit Specifyforyourhealth111-pixel/Vibe-Skills3.6k—~3.3kAutomated safety check: PassApache-2.0

Similar skills

  • Defer Async

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Load scripts with defer, async, or type=module.

    74k GitHub stars~494 tokensUpdated yesterday
    Auto-check passed

  • Specify

    ZaxbyHub/opencode-swarm

    Full execution protocol for MODE: SPECIFY -- spec creation, codebase reality checks, SME input, QA gate persistence, and optional council spec review.

    490 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Delay Claim Letter

    mohitagw15856/pm-claude-skills

    Draft a construction delay notice or delay claim letter with contract clause citation, cause classification, and critical-path impact narrative.

    1.4k GitHub stars~1.6k tokensUpdated today
    Research & ScienceAuto-check passed

  • Specify

    team-attention/hoyeon

    "/specify", "specify", "요구사항 정의", "requirements", "스펙 잡기", "뭘 만들어야 하는지", "기획 정리", "인터뷰해서 스펙" Turn a goal into structured requirements through systematic interview.

    173 GitHub stars~7k tokensUpdated 4 mo ago
    Auto-check passed

  • Speckit Specify

    foryourhealth111-pixel/Vibe-Skills

    Create or update feature specifications from natural language descriptions.

    3.6k GitHub stars~3.3k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Spk Mission Specify

    spec-kitty/spec-kitty

    Operate the Spec Kitty specify phase: turn user intent into a mission spec while preserving scope, ambiguity, and acceptance criteria.

    1.7k GitHub stars~269 tokensUpdated today
    Product & Project ManagementAuto-check passed

More from sammcj/agentic-coding

All 62 skills in this repo

  • Yue2 Music

    sammcj/agentic-coding

    A skill your agent uses when generating songs with YuE2, covering a recording via SheetSage2 audio-to-ABC, editing a score or lyrics with melody preservation, or building a reproducible listening…

    162 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Bento Slides

    sammcj/agentic-coding

    A skill your agent uses when creating or editing Bento (.bento.html) slide decks, including any request for a single-file HTML slide deck.

    162 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Idrive Backup

    sammcj/agentic-coding

    A skill your agent uses whenever the user wants you to manage, discuss or diagnose iDrive Backup configuration on macOS

    162 GitHub stars~1.7k tokensUpdated today
    Auto-check: notes

  • Piper Tts Training

    sammcj/agentic-coding

    Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches.

    162 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • PPTX To Md

    sammcj/agentic-coding

    Convert a PPTX slide deck into per-slide markdown that preserves both the verbatim text and the meaning of embedded screenshots, diagrams and charts in their original layout positions.

    162 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Skill Creator Primer

    sammcj/agentic-coding

    You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill.

    162 GitHub stars~9.8k tokensUpdated today
    Auto-check passed

Questions about Deferred Task Execution

What does Deferred Task Execution do?

Delays execution of a task until a specified time or after a duration. Deferred Task Execution is an agent skill from sammcj/agentic-coding. Delays execution of a task until a specified time or after a duration.

When should I use Deferred Task Execution?

Deferred Task Execution fits situations like: the user asks to run something later; in X minutes/hours; at a specific time; schedule a command.

How do I install Deferred Task Execution in Claude Code?

Run `npx skills add sammcj/agentic-coding --skill deferred-task-execution -a claude-code`. Or copy the skill folder (Skills/deferred-task-execution in sammcj/agentic-coding) into .claude/skills/deferred-task-execution in your project. Claude Code loads it when a task matches its description.

How do I install Deferred Task Execution in Codex?

Run `npx skills add sammcj/agentic-coding --skill deferred-task-execution -a codex`. Or copy the skill folder (Skills/deferred-task-execution in sammcj/agentic-coding) into .agents/skills/deferred-task-execution in your project. Codex loads it when a task matches its description.

Can I use Deferred Task Execution in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sammcj/agentic-coding --skill deferred-task-execution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deferred-task-execution, .gemini/skills/deferred-task-execution, .github/skills/deferred-task-execution and .opencode/skills/deferred-task-execution in your project.

What does Deferred Task Execution need to run?

Going by SKILL.md and its folder, Deferred Task Execution needs a shell for the scripts in its folder. Our summary lists: A Bash shell. Its frontmatter pre-approves these tools: Bash, Read, TaskStop.

Does Deferred Task Execution access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deferred Task Execution safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Deferred Task Execution use?

Deferred Task Execution is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deferred Task Execution use?

About 642 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deferred Task Execution?

Skills that share tags, products or a category with Deferred Task Execution: Defer Async (thedaviddias/Front-End-Checklist, 74k stars), Specify (ZaxbyHub/opencode-swarm, 490 stars), Delay Claim Letter (mohitagw15856/pm-claude-skills, 1.4k stars) and Specify (team-attention/hoyeon, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deferred Task Execution?

sammcj (a GitHub user) maintains it in sammcj/agentic-coding, which has 162 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 7, 2026.

Source: sammcj/agentic-coding on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.