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.
npx agentmods add skills/aksika/abtars/create-tasknpx skills add aksika/abtars --skill create-taskgit clone --depth 1 https://github.com/aksika/abtarsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00024 | $0.01969 |
| Opus 5 | $0.00012 | $0.00984 |
| Sonnet 5 | $0.00005 | $0.00394 |
| Haiku 4.5 | $0.00002 | $0.00197 |
Grade A, and why
create-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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Scheduled Task
Choose the task kind, register the definition, and verify it. Tasks are scheduler definitions under ~/.abtars/tasks/; skills are reusable procedures loaded on demand.
Choose the task shape
| Need | Definition |
|---|---|
| Send fixed text | kind: reminder, delivery: announce |
| Run a shell command without a model | kind: script |
| Run one agent session and return text | kind: agent, interaction.mode: oneshot, delivery: announce |
| Generate and deliver a file | kind: agent, interaction.mode: oneshot, delivery: report plus a report contract |
| Start or resume a conversation | kind: agent, interaction.mode: skill, delivery: announce |
| Run an internal bridge action | kind: system, delivery: silent |
Use the CLI for simple reminders, scripts, system actions, and announce-mode agent oneshots. Advanced definitions such as reports, interactive launches, orchestration, follow-ups, or policy limits require a careful read/modify/write of ~/.abtars/tasks/tasks.json.
Common contract
- Use a lowercase kebab-case
id. The CLI normalizes input and rejects duplicates. - Set exactly one of
schedule(five-field cron:minute hour day month weekday) orat(a parseable one-shot date/time). Include an explicit timezone offset inatwhen the intended timezone matters. - Set
deliveryexplicitly in hand-written JSON. - Optional common fields are
enabled,priority(high,medium, orlow),chatId,catchUpHours, andmaxRunsPerDay. - Preserve every unrelated entry when editing
tasks.json. It must remain a JSON array. - Do not edit
task-state.jsonortask-history.jsonl; the runtime owns them. - Unknown top-level fields quarantine the affected definition. Use only these kind-specific fields:
| Kind | Kind-specific fields |
|---|---|
reminder |
text |
agent |
prompt, taskFile, agent, orchestration, interaction, report, maxToolRounds |
script |
command, followUp |
system |
action, options |
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.
- 2d ago First seen · 169 lines · 24 tokens per session scan A 5fa8de264c38
create-task is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,969 once invoked, about $0.0001 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.
Other skills, from other repositories
agent-quorum-manager
Agent skill for quorum-manager - invoke with $agent-quorum-manager.
agent-agent
Agent skill for agent - invoke with $agent-agent.
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
agent-adaptive-coordinator
Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator.
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-load-balancer
Agent skill for load-balancer - invoke with $agent-load-balancer.