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 9b1241732f3agit 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/9b1241732f3a)<a href="https://agentmods.dev/skills/orkas-ai/orkas/9b1241732f3a"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/9b1241732f3a/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/9b1241732f3a"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/9b1241732f3a.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 | $0.00002 | $0.00765 |
| Opus 5 | $0.00001 | $0.00382 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
product-test 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Test
Use this skill to define the observable behavior that must be true for a story or feature to be considered done. It turns product context into concise, testable Given/When/Then scenarios that engineers and QA can verify without guessing intent.
Do not use this skill to write a full PRD, redesign the feature, break work into engineering tasks, write implementation plans, run tests, write automation code, or create exhaustive test suites. Stay focused on product-level acceptance scenarios for a specific story, feature slice, or behavior.
When To Use
- A user story, PRD section, or feature slice already exists.
- The team needs clear pass/fail conditions before or during implementation.
- QA needs explicit happy path, edge case, error state, or non-functional scenarios.
- A story is too vague and needs observable done conditions.
If the feature scope is unclear, ask for the smallest missing context before drafting criteria.
Instructions
- Confirm the slice: identify the exact story, workflow, user role, or behavior being accepted.
- Capture inputs and assumptions: list source material, scope boundaries, and missing context.
- Separate scenario types: cover happy path first, then edge cases, error states, and non-functional expectations.
- Use stable acceptance IDs and Given/When/Then only: each criterion should be independently testable and observable so engineering evidence can map back to it.
- Describe recovery behavior: when validation fails or a dependency breaks, state what the user sees and how they can recover.
- Avoid implementation leakage: do not mention internal classes, tables, functions, or code paths unless the acceptance surface is technical by nature.
- Review for pass/fail clarity: rewrite subjective criteria into measurable outcomes.
- End with handoff: state what is ready for QA or engineering, what still needs clarification, and the observable evidence surface for each acceptance ID without prescribing implementation details.
What ships with it
2 files 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.
- 11d ago First seen · 57 lines · 2 tokens per session scan A 3912844e843b
product-test is a skill published in the GitHub repository Orkas-AI/Orkas (1,885 stars, last pushed yesterday), licensed MIT. It adds 2 tokens to every session and 765 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
browser-qa-report
Runs a read-only browser QA pass and returns evidence.
factory-render-verify
Render-and-measure receipts for any HTML page your factory builds — the render half of the design quality gate. Engineer runs it to screenshot every screen size and MEASURE what a source read or a single screenshot only guesses at: horizontal overflow, computed type sizes, tap-target sizes, safe-area presence, mono…
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
relay-80-100-workflow
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes review/fix loops…