task

A task manager for creating scheduled agent jobs. Each job has instructions, supporting files, a schedule, and a record of its runs.

In plain words
What is it for?
Use it for daily reports, regular checks, reminders, or other agent actions that should run on a schedule.
Why use it?
It removes the need to remember recurring work or start it manually. It keeps each scheduled job's instructions and related data together.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aksika/abtars/task
Any agent
npx skills add aksika/abtars --skill task
Clone the repo
git clone --depth 1 https://github.com/aksika/abtars

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 969 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00969
Opus 5 $0.00000 $0.00485
Sonnet 5 $0.00000 $0.00194
Haiku 4.5 $0.00000 $0.00097

Measured 2d ago against content hash af69a6d9db54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task 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 2d 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.

templates/skills/task/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Management

Create, edit, and manage scheduled tasks. Tasks live at ~/.abtars/tasks/ — each task is a directory.

Structure

~/.abtars/tasks/
├── tasks.json              # Registry: schedule, kind, taskFile path (definitions only)
├── task-state.json          # Runtime state (auto-managed, do not edit)
├── task-history.jsonl       # Append-only run log (auto-managed)
├── my-task/
│   ├── TASK.md              # Main prompt (what the agent does)
│   ├── feeds.json           # Associated data (auto-injected)
│   └── report-template.md   # Any supporting files

All files in a task directory (except TASK.md) are automatically injected as context when the task runs.

Creating a task

  1. Create the directory and TASK.md:
mkdir -p ~/.abtars/tasks/my-task
cat > ~/.abtars/tasks/my-task/TASK.md << 'EOF'
# My Task

Instructions for what the agent should do when this task fires.
Use {today} for today's date (auto-substituted).
EOF
  1. Register in tasks.json via CLI:
abtars-task add \
  --id my-task \
  --schedule "0 9 * * *" \
  --message "Run my-task" \
  --kind agent \
  --agent task \
  --task-file "~/.abtars/tasks/my-task/TASK.md" \
  --chat-id <CHAT_ID>

Schedule format

Standard cron: minute hour day month weekday

Example Meaning
0 9 * * * Daily at 9am
30 8 * * 1-5 Weekdays at 8:30am
0 0 * * * Midnight daily
0 */6 * * * Every 6 hours

For one-shot tasks, use --at "2026-12-25T08:00" instead of --schedule.

Task kinds

Kind Behavior
agent Agent session runs the prompt or TASK.md
script Shell command runs directly
reminder Simple text reminder at scheduled time
orc Orc project dispatch
system Internal bridge action (sleep-cycle, hardware-sleep)

Delivery modes

Set delivery in tasks.json. Each kind has a required delivery mode.

Mode Behavior Use for
report Drop the result file to chat (no model call) Reports, generated documents
announce Send the agent's response text directly Greetings, conversational tasks
silent No output to user Internal housekeeping, scripts

Read the full file on GitHub · 118 lines

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. 2d ago First seen · 118 lines · 0 tokens per session scan A af69a6d9db54

Subscribe to this mod's changes

task is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 969 tokens. 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.