schedule-tasks

schedule-tasks is a skill for Claude Code from Xakki/ai-agents-skills. It costs 128 tokens per session (2,486 once invoked), scanned A, original, MIT.

A skill for scheduling Claude runs to work through eligible Kanban cards, which are task cards arranged by work status. It uses the at scheduler and separate byobu or tmux windows for each run.

In plain words
What is it for?
Use it to run todo cards on a timer, move cards through implementation and testing stages, and pause tasks that need escalation.
Why use it?
It removes the need to start each queued task manually and can continue to the next card after a run finishes, while leaving final completion to the user.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: names the AskUserQuestion tool; positional $N argument; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ai-agents-skills plugin — 23 skills, 3 agents, 6 hooks shipped together

Good fit Use it to run todo cards on a timer, move cards through implementation and testing stages, and pause tasks that need escalation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Xakki/ai-agents-skills
Claude Code
/plugin install ai-agents-skills

Made for: Claude Code.

Or install ai-agents-skills, the plugin that ships this one along with the rest of its 23 skills, 3 agents, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for schedule-tasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/xakki/ai-agents-skills/schedule-tasks/github.svg)](https://agentmods.dev/skills/xakki/ai-agents-skills/schedule-tasks)
Your own site
<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/schedule-tasks"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/schedule-tasks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for schedule-tasks

Your own site · 80×15
<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/schedule-tasks"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/schedule-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,486 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00128 $0.02486
Opus 5 $0.00064 $0.01243
Sonnet 5 $0.00026 $0.00497
Haiku 4.5 $0.00013 $0.00249

Measured 10d ago against content hash 3b38152ffb4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

schedule-tasks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/schedule-tasks/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Schedule one-shot autonomous claude runs for cards in .claude/kanban/todo/. Each job opens a byobu window in session 1, walks one card todo→progress→test→ready, then self-chains the next card at +20 min on ok, park, or skip. Chain STOPS only when atd is inactive or the backlog has no eligible card. Final hop ready→done is user-only. Escalation parks non-blocking on a task/* branch; resume via /schedule-tasks resume.

Git mechanics follow the git-flow core. The autonomous per-task branch + park-commit + bulk-stage-on-resume model below is this skill's documented exception to that core.

Commit shape + lifecycle → lifecycle.md. Script internals, session IDs, log paths, edge cases → reference.md.

Tools

Tool Purpose
at / atq / atrm / at -c <N> One-shot scheduler (preferred over cron)
tmux -S /tmp/tmux-1000/default Talk to the user's byobu session

atd must be active (systemctl is-active atd). Window naming format → reference.md.

Workflow

1. Clarify with the user — ASK ONLY when needed

Defaults (do NOT ask):

  • Branch = current branch. Commit shape per card: 4 commits (happy path) —
    1. task: start <ID> (todo→progress) — git mv only, own commit;
    2. implementation commit(s) (scope: api|db|infra|docs|task, per git-flow) — code + Execution Log;
    3. task: review <ID> (progress→test) — git mv only, own commit;
    4. task: ready <ID> (test→ready) — git mv only, own commit. Full details → lifecycle.md.
  • Order = chain picks the next card itself (related-first, then lex-oldest — see lifecycle.md).

Ask only for:

  • Ambiguous date/time — "через час" (in an hour) / "вечером" (in the evening) when already past that. Skip if user gave at -t YYYYMMDDhhmm-style precision.
  • User-stated constraints that need confirmation ("только front-* задачи" (only front-* tasks), "не трогай DB" (don't touch DB), "после каждой задачи e2e" (e2e after each task) — confirm prefix / scope / command).

Read the full file on GitHub · 173 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 173 lines · 128 tokens per session scan A 3b38152ffb4b

Subscribe to this mod's changes

schedule-tasks is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 20d ago), licensed MIT. It adds 128 tokens to every session and 2,486 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

timeline-creator

Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.

mhattingpete/claude-skills-marketplace · 47 tokens

specs

Use when a rough user story, bug report, feature idea, piece of feedback, or an implementation plan should be recorded as a GitHub issue — "file a ticket for this", "open an issue", "write this up for the backlog", "we should track this", "log this bug", "spec this out as a ticket so we can pick it up later" — i.e.…

The01Geek/prflow · 125 tokens

process-doc

Turn an operational process into a clear SOP, role model, control map, and improvement backlog.

KunAgent/Kun · 22 tokens

ag-pipeline-issue

Pipeline Issue→SPEC→Build→Verify→Test. Toda GitHub Issue gera SPEC antes de implementar, e toda implementacao e verificada contra a SPEC e testada. Use when starting work on a GitHub Issue.

andregusman-raiz/a-gusman-claude · 51 tokens

ag-team-terminais

Protocolo para 2+ sessoes Claude interativas em terminais separados trabalharem no MESMO repo com objetivos distintos. Coordenador + workers, manifesto duravel em docs/ai-state/team/, mensagens nativas via ListAgents/SendMessage, worktree por worker. Modos: init | join | status | fechar. Para teammates dentro de UMA…

andregusman-raiz/a-gusman-claude · 86 tokens

ag-registrar-issue

Registra GitHub Issues para problemas nao resolvidos imediatamente. Recebe contexto via SendMessage de outros agents. Dedup, labels, severidade. Use when an agent finds a problem it cannot fix now.

andregusman-raiz/a-gusman-claude · 49 tokens