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 88aca13869d9git 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/88aca13869d9)<a href="https://agentmods.dev/skills/orkas-ai/orkas/88aca13869d9"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/88aca13869d9/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/88aca13869d9"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/88aca13869d9.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 | $0.00001 | $0.00911 |
| Opus 5 | $0.00000 | $0.00456 |
| Sonnet 5 | $0.00000 | $0.00182 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
github 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub
Use gh as the primary interface for GitHub data and actions. Keep this skill focused on basic operations and command safety, not maintainer triage strategy.
Before Running Commands
- Confirm
ghexists and is authenticated when live GitHub data is required. - Prefer
--repo owner/repounless the current directory is clearly inside the intended GitHub repository. - Use
--jsonand--jqwhen the result will be summarized or filtered. - Read-only inspection never needs approval. Resolve the repository, exact object, current state, policy, and relational targets before a write.
- A current user request authorizes the exact write, direct target, relational target, and stated conditions it specifies. Do not add a second confirmation after preflight succeeds.
- If the repository or target is unresolved, ask only for the missing target and retain the action authority already granted by the request.
- When owner/repository itself is missing, ask directly for
owner/repo; do not substitute a local checkout path, account hint, account switch, or organization search for that canonical target. - Bound target discovery to supplied references and the current repository remote. If those do not resolve owner/repository, ask immediately; do not enumerate accounts, organizations, or unrelated repositories.
- Ask for new approval only when execution requires a material scope expansion, such as a different repository or object, an extra write, force mode, or admin override. For force/admin/policy-bypass decisions, leave the choice unselected or default to stopping with state unchanged; do not offer a speculative retry or preselect escalation.
- Honor authentication, permission, deletion, billing, or other platform-required confirmation gates exactly once; do not duplicate them in prose.
- For a finite maintainer request, batch independent preflight reads in one tool round, authorized independent writes in the next, and final state verification in one last read round. Do not interleave narrative plan updates or repeat unchanged reads.
- Choose exactly one remote branch-deletion mechanism. If
gh pr merge --delete-branchis used, verify absence afterward instead of issuing another delete; otherwise merge without that flag and delete the resolved head ref once.
What ships with it
1 file 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.
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.
- 12d ago First seen · 55 lines · 1 tokens per session scan A b37091f97c10
github is a skill published in the GitHub repository Orkas-AI/Orkas (1,885 stars, last pushed yesterday), licensed MIT. It adds 1 tokens to every session and 911 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 2026-08-30.
Other skills, from other repositories
workspace-diff-review
Reviews the current workspace diff with a pre-landing mindset.
devops-assistant
Assists in version control, deployment, and automation tasks, ensuring smooth DevOps operations and workflow efficiency.
release-doc-sync
Prepares or applies bounded documentation updates for the current workspace changes.
release-readiness-check
Runs the existing repo checks that already exist, then turns the raw outcomes into a short readiness report with blockers and next actions.
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.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.