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 seo-backlink-valuegit 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/seo-backlink-value)<a href="https://agentmods.dev/skills/orkas-ai/orkas/seo-backlink-value"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/seo-backlink-value/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/seo-backlink-value"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/seo-backlink-value.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 | $0.00004 | $0.02367 |
| Opus 5.5 | $0.00002 | $0.00947 |
| Sonnet 5.5 | $0.00001 | $0.00473 |
| Haiku 4.5 | $0.00000 | $0.00237 |
Grade A, and why
seo-backlink-value 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seo-backlink-value
Value a backlink offer the way a buyer should: veto bad sites first, then price the good ones against a market band and the seller's quote. Deterministic, stdlib-only, no network. The agent supplies the metrics; this skill only computes.
When to use
- The user has one or more link offers (guest post, homepage/sitewide, niche edit, directory listing, nofollow/sponsored) and asks whether to buy, what a fair price is, or which to buy first.
- A strategy or off-page recommendation needs a defensible price ceiling for a proposed link placement.
When NOT to use
- Discovering candidate sites or fetching DR, traffic, or keyword data. Those come from the user, a connected console, or a paid tool the user already has; this skill has no data source of its own.
- On-page, technical, or GEO scoring of the user's own site (
seo-tech-audit,geo-score).
Acquire the metrics before calling (agent work)
The user should not have to look numbers up. Fill each offer's metrics in this
order and record the source of every value in sources:
- A connected SEO data provider (Ahrefs, Semrush, Moz, DataForSEO,
SimilarWeb, SE Ranking) through the connector tools: list the connected
tools, call the domain-overview / backlink-profile operation, and map DR or
DA, monthly organic traffic, organic share, trend and referring domains
into
metricswithsourcesnaming the provider. These are the only figures that may be reported as provider-measured. - Free public endpoints with
web_fetchwhen no provider is connected. Pass what they return inproxies; the skill converts them into conservative tier estimates and labels the whole resultpublic_proxy:- Popularity rank and 30-day history:
https://tranco-list.eu/api/ranks/domain/<domain>→{"domain","ranks":[{"date","rank"}]}. Put the latestrankinproxies.tranco_rank(ornullwhen the response lists no ranks) and the full array inproxies.tranco_history. - Domain age: RDAP. Look up the TLD's server in
https://data.iana.org/rdap/dns.json, then fetch<server>/domain/<domain>(for .com/.net:https://rdap.verisign.com/com/v1/domain/<domain>) and pass theregistrationevent'seventDateasproxies.rdap_registration. - Indexation: a
web_searchforsite:<domain>; pass the visible result count asproxies.site_results(0 leaves indexation unknown). Setmetrics.indexed: falseonly from verified index-status evidence, not search absence. Organic share has no free source; leave it out and say so.
- Popularity rank and 30-day history:
- Ask the user only for what steps 1–2 could not supply, naming the exact field. Never scrape the web UI of Ahrefs, SimilarWeb, Semrush or Moz free checkers: they are login- or CAPTCHA-gated and their terms forbid it.
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.
- 1mo ago First seen · 102 lines · 4 tokens per session scan A 993a3a89d94c
seo-backlink-value is a skill published in the GitHub repository Orkas-AI/Orkas (2,192 stars, last pushed today), licensed MIT. It adds 4 tokens to every session and 2,367 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 2026-09-12.
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.