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 image-composegit 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/image-compose)<a href="https://agentmods.dev/skills/orkas-ai/orkas/image-compose"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/image-compose/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/image-compose"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/image-compose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 78 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.02467 |
| Opus 5.5 | $0.00001 | $0.00987 |
| Sonnet 5.5 | $0.00000 | $0.00493 |
| Haiku 4.5 | $0.00000 | $0.00247 |
Grade A, and why
image-compose 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Compose
Read this skill after route lock for COMPOSE, or later in HYBRID, GENERATE, or EDIT only when deterministic copy, layout, diagram, framing, crop, mask, or overlay work is required. Do not preload it during routing. Keep the artifact in one stable directory containing image-manifest.json, index.html, and local assets.
Safe project bootstrap
Create or repair image-manifest.json and index.html with write_file / edit_file. Do not assemble either file through bash, PowerShell, shell redirection, or an inline script: quoting damage can leave a partially written project and shell safety checks can block recovery.
This production skill is the earliest point at which a COMPOSE manifest may be created. Initialize it from the Canonical image-manifest v1 block in image-router; that block is the single structural source, so do not redefine or reconstruct the manifest shape here. Replace every example value with the current brief and planning output. Keep its nesting and value types exactly: brief.purpose and every art_direction field are required by native inspection, and any region coordinates belong under visual_plan.regions[].bounds.
For HYBRID, GENERATE, or EDIT, keep the locked lowercase route and the approved generation budget (zero for deterministic EDIT), then add the route-specific reference and request fields required by image-router / image-generate. After the first write, read the manifest back once and repair it with edit_file if needed before calling project.inspect.
Declare one final source: entry for an HTML composition, or raster_source for a finished raster. Remove the other final-source field when the candidate changes form; keep generated layers as local HTML assets. Set entry explicitly for HTML work under EDIT or GENERATE. After a script transform, bind its actual output as raster_source and inspect that path.
Authoring contract
- Start from the canvas and art direction in the manifest. Make the first render meaningful without network access or user interaction.
- Keep decorative rules, strokes, and signature geometry outside every required-text bounding box. After any headline revision, recheck the full phrase at thumbnail size and repair any line or shape that crosses, crowds, masks, or visually splits a glyph or line of copy.
- Fit every multi-glyph required headline as a complete phrase before snapshot. Automatic wrapping must never leave a line with only one glyph: widen the text box, reduce the type size, or author an intentional balanced
<br>before capture. Do not approve a source merely because the DOM contains the exact string; line-by-line rendered legibility is the gate. - For a multi-image set, reuse the first passing image's concrete CSS/SVG design decisions—palette variables, type roles, spacing/grid, radii, strokes, icon treatment, material effects, and signature device—in every later member. Change the content and the layout details needed by that content; do not redesign the visual system per image.
- Use semantic HTML for text and SVG for geometry, diagrams, strokes, charts, patterns, and masks. Use CSS for layout, texture, lighting, and controlled effects.
- Preserve every required-copy string exactly in visible DOM text. Keep important text out of raster assets.
- For COMPOSE copy revisions in a supplied raster, cover only the old text area and typeset the replacement as a complete glyph or text run; guessing extra strokes onto raster digits can leave the old number readable. Match the original typeface, weight, size, color and baseline, and preserve the surrounding pixels. Verify the replacement in the current snapshot at export size against the source: dimensions, a changed-pixel box, and image metadata do not prove that the visible wording or its styling is correct.
- Preserve natural English casing: use sentence case or natural title case for titles and sentence case for body, captions, labels, and CTAs. Keep all caps only when that exact casing is explicit in required user copy or an external brand/source, and then only for one short metadata label, acronym, or code. Never apply
text-transform: uppercasethrough a broad selector or use multiple all-caps text roles; create hierarchy with family, width, weight, scale, color, or spacing. - Use only local relative assets inside the project directory. Do not use scripts, CDNs, remote fonts, remote images, iframes, embedded pages, autoplay media, or a local server.
- In
HYBRID, use the generated raster as one deliberate layer and let HTML/SVG own copy, logo placement, framing, and layout. - Map every
visual_plan.regions[].idto an HTML/SVG element withdata-image-region. Treat supplied reference images as local assets: they remain usable in HTML through<img>, CSS backgrounds, SVG<image>, masks, crops, and overlays without a generation call. - Declare the fixed canvas on the
index.htmlroot withdata-preview-layout="fixed-canvas",data-preview-width="<canvas.width>", anddata-preview-height="<canvas.height>". The two dimensions must exactly matchimage-manifest.json; this is the shared HTML viewer contract, not ImageStudio-specific presentation logic. - Size for the declared canvas. Avoid hidden overflow, tiny copy, edge collisions, and low-contrast focal content.
What ships with it
3 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.
- 1mo ago Changed · +7 lines 6286a9295332
- 1mo ago First seen · 81 lines · 2 tokens per session scan A f37b856e8204
image-compose is a skill published in the GitHub repository Orkas-AI/Orkas (2,152 stars, last pushed yesterday), licensed MIT. It adds 2 tokens to every session and 2,467 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 2026-08-30.
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.