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 skills add aksika/abtars --skill taskgit clone --depth 1 https://github.com/aksika/abtarsWrote 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.
[](https://agentmods.dev/skills/aksika/abtars/task)<a href="https://agentmods.dev/skills/aksika/abtars/task"><img src="https://agentmods.dev/badge/skills/aksika/abtars/task/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.
<a href="https://agentmods.dev/skills/aksika/abtars/task"><img src="https://agentmods.dev/badge/skills/aksika/abtars/task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 22 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00969 |
| Opus 5.5 | $0.00000 | $0.00388 |
| Sonnet 5.5 | $0.00000 | $0.00194 |
| Haiku 4.5 | $0.00000 | $0.00097 |
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 1mo 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 — 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
- 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
- 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 |
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.
- 1mo ago First seen · 118 lines · 0 tokens per session scan A af69a6d9db54
task is a skill published in the GitHub repository aksika/abtars (10 stars, last pushed today), 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.
Other skills, from other repositories
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
moai-factory-foreman
One unattended factory foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
task-list
Required for 4+ step requests; add tasks at start and update status after each step.
cog-onboarding
Personalize COG Second Brain workflow through role pack selection and vault initialization.
moai-todo
Compatibility alias for the canonical GTD task-management entry point.