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 package-installergit 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/package-installer)<a href="https://agentmods.dev/skills/orkas-ai/orkas/package-installer"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/package-installer/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/package-installer"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/package-installer.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 | $0.00003 | $0.01222 |
| Opus 5 | $0.00002 | $0.00611 |
| Sonnet 5 | $0.00001 | $0.00244 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
package-installer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package Installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
Run the Orkas CLI command below through the command execution tool; Orkas handles this runner form directly on Windows:
"$ORKAS_NODE" "$ORKAS_PC_DIR/bin/orkas-pkg.cjs" <command> [args]
Commands: install <git-url> [--name <name>] [--consent-deps],
consent-deps <name>, update <name>, remove <name>, list,
info <name>.
Every command prints a JSON result; non-zero exit prints {ok:false,error}.
Install flow
- Run
install <git-url>. Use--name <name>when the user, marketplace prompt, or install request explicitly gives a package name, or when the repo basename is not a valid package name (the error message will say so). Never pass--consent-depson the first attempt — dependency installs need the user's explicit approval first. - Read the JSON result:
deps_pending_consentnon-empty → the package is installed but its dependencies are not. Show the user the exact commands listed there and ask for approval; after they agree, runconsent-deps <name>. If they decline, leave it as is — skills that need no deps still work.errormentioning "not installable" → tell the user the project has neither skills (SKILL.md) nor CLI entry points and is not supported (agent-driven-only projects cannot be installed).
- Report what was installed, from the result fields:
skill_rootsnon-empty → its skills become available in new turns.shimsnon-empty → those commands are directly callable from the host shell/PATH in the next turn (e.g.hyperframes --help). On Windows the installer creates.cmdshims for CLI entries.
Author a usage skill for CLI-only installs
When the install result is kind: "cli" (empty skill_roots, non-empty
bin_entries), author a companion usage skill so future turns get curated
instructions instead of a bare command list. Do this automatically right after
a successful CLI install — the user already approved installing it. Skip for
kind: "skill" and kind: "both" (they already ship their own SKILL.md).
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.
- 5d ago First seen · 102 lines · 3 tokens per session scan A 99a02f6341bd
package-installer is a skill published in the GitHub repository Orkas-AI/Orkas (1,808 stars, last pushed yesterday), licensed MIT. It adds 3 tokens to every session and 1,222 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
tutti-workspace-app-factory
Create, convert, or repair one Tutti workspace app as either a self-contained publishable package under package/ or a Chrome-style local debug app under .tutti/dev-app/. Use for mention://workspace-app-factory/create handoffs, mention://workspace-app-factory handoffs, standalone app generation, adapting existing…
tutti-ui-system
Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.
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 that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
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.
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.