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 voice-projectgit 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/voice-project)<a href="https://agentmods.dev/skills/orkas-ai/orkas/voice-project"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/voice-project/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/voice-project"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/voice-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00504 |
| Opus 5.5 | $0.00001 | $0.00202 |
| Sonnet 5.5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
voice-project 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 24d 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.
What it actually says
Voice Project
Choose only the route needed for the current audio deliverable:
- Text narration, multi-role scripts or a spoken-segment revision: read narration.md.
- Recording transcription, local cuts, mixing or export: read local-audio.md.
- Both routes use project-format.md when creating or changing project files.
Use the host-bound Skill execution reference for scripts/audio.js; invoke script basename audio with the operation and a workspace JSON request file as its two arguments. The host supplies Node, FFmpeg/FFprobe and Whisper/model paths. preflight needs no request file and reports availability only; it does not install anything. Missing binaries/models require an application repair/update. Never install packages, download models, or replace bundled components during a task.
Write required request JSON with workspace file tools before invoking the script. Use the host command template for one audio operation per command, with a quoted absolute request-file path. Prepare media separately; keep loops and computed paths out of the invocation command because unresolved targets require approval.
Keep one topic-named project directory in the current workspace. Copy supplied media into its sources/ directory through existing scoped file/shell tools before referencing it. Preserve originals. Saved project paths are relative to this directory; no external paths or symlink escapes. All script request files contain an absolute project path to voice-project.json. Run project mutations sequentially.
Core capabilities use configured TTS and local codecs/transcription. Background music and effects are supplied files. Voice cloning/design, generated music, source separation, diarization and professional restoration are outside this package's declared capability. Do not silently approximate one of those requests as a supported operation.
Exports retain prior candidates and include a receipt of objective checks. Publish only requested user-facing outputs through the existing file-publication surface. Link audio for playback using the host's file/media result; do not describe generated speech or transcription as personally listened to when no listening evidence exists.
What ships with it
4 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.
- 24d ago First seen · 25 lines · 2 tokens per session scan A ce3136af0b6a
voice-project is a skill published in the GitHub repository Orkas-AI/Orkas (2,192 stars, last pushed today), licensed MIT. It adds 2 tokens to every session and 504 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
takt
A workflow engine for coordinating multiple coding agents. It reads a YAML workflow, a text configuration format, and moves agents through its defined steps and rules.
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
create-coordclaw-team
A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.
write-file
Replaces OpenClaw built-in write tool for all plain text writing, providing.
skill-structure-advisor
Helps you choose the right design pattern and structure for a new skill.