Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
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 Orkas-AI/Orkas --skill autotask-creatorgit clone --depth 1 https://github.com/Orkas-AI/OrkasWrote 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/orkas-ai/orkas/autotask-creator)<a href="https://agentmods.dev/skills/orkas-ai/orkas/autotask-creator"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/autotask-creator/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/orkas-ai/orkas/autotask-creator"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/autotask-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00005 | $0.01749 |
| Opus 5 | $0.00003 | $0.00874 |
| Sonnet 5 | $0.00001 | $0.00350 |
| Haiku 4.5 | $0.00001 | $0.00175 |
Grade A, and why
autotask-creator 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 6d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/auto_tasks files directly. It emits one or more top-level <auto-task>...</auto-task> containers in its final text; the bus parses and applies them after the turn.
When to use this skill
Use this Skill when the user asks to:
- Create an automation / auto task / scheduled reminder.
- Update an existing automation's content, title, schedule, recipient, skill, connector, project scope, attachments, or enabled state.
- Delete, enable, or disable an automation.
Hard rules
- Mutations only via
<auto-task>container. Do not use file tools or shell commands to write/delete auto task configs. - Read before edit/delete. For update, delete, enable, or disable, call
auto_tasks_listfirst unless the current user message already contains the exacttask_id. - No guessed IDs. If multiple tasks could match, ask one concise clarification instead of emitting a container.
- Partial updates are expected. For update, output only
<task_id>,<action>update</action>, and the fields being changed. Never re-emit a full task unless several fields truly changed. - Top-level raw block. Containers must not be fenced, quoted, or wrapped in markdown lists.
- One task per container. Use multiple containers only when the user explicitly asks to change multiple automations.
- Keep content clean.
<content>stores the user-facing instruction only; do not include@agenttext, skill-use prefixes, or connector-use prefixes. Use<recipient>,<skill>, and<connector>fields instead. - Container first; visible prose stays brief and non-authoritative. Emit the raw container(s) before any optional summary. Do not repeat the full JSON in prose, and do not use past-completion wording such as "已按要求改好", "created", "updated", or "deleted" before the host applies the container. If a summary is useful, use pending wording such as "将把时间改为周五 10:00"; the host appends the authoritative success or failure result.
- Keep internal ids out of clarification copy. Use titles, schedule times, project names, or content snippets to distinguish candidates. Show a
task_idonly when the user explicitly supplied or requested it.
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.
- 6d ago First seen · 129 lines · 5 tokens per session scan A b7d37b9fa792
autotask-creator is a skill published in the GitHub repository Orkas-AI/Orkas (1,848 stars, last pushed yesterday), licensed MIT. It adds 5 tokens to every session and 1,749 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
extract-action-items
Extract a list of action items with owners and deadlines from a meeting transcript.
factory-update
Explains and drives the factory's update path — how improvements to the public template reach this office as a human-gated pull request. Invoke when the human asks 'is my factory up to date?', when a factory-update PR needs explaining hunk by hunk, or when an update was declined and needs a selective re-apply.
factory-retro
The factory learning to run itself better. Explicit-invoke: run when the human asks for a retro ('how are we doing?', 'what keeps going wrong?', '/factory-retro'), or on a schedule the human sets. Reads the journal end to end, finds friction patterns — repeated misses, slow handoffs, rules that keep tripping…
antigravity-agent-manager
Configure and orchestrate parallel agents using the standalone Antigravity 2.0 Agent Manager and Antigravity IDE.
task-tracker
A file-based task list for adding, completing, viewing, prioritising, and archiving to-do items.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.