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 08837be6032egit 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/08837be6032e)<a href="https://agentmods.dev/skills/orkas-ai/orkas/08837be6032e"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/08837be6032e/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/08837be6032e"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/08837be6032e.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 | $0.01365 |
| Opus 5.5 | $0.00001 | $0.00546 |
| Sonnet 5.5 | $0.00000 | $0.00273 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
data-analysis 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analysis
Derive reviewable conclusions from the user's data. Use the available source and computation tools; this Skill does not prescribe a format, language, library, or artifact. Respect project metric definitions and business rules. Preserve inputs unless transformation was requested, and match effort to the decision's risk.
Apply three gates before analysis:
- Precision gate: execute precision-preserving arithmetic before reporting an exact monetary/ledger reconciliation or another result where ordinary numeric arithmetic can lose meaningful digits. Reading values, profiling them, or writing out arithmetic is not verification.
- Method gate: report no statistical interval, p-value, model coefficient, forecast, or probability unless an applicable method was executed and its assumptions are supported by the evidence. Calling a number rough or approximate does not supply a derivation.
- Confidence gate: return no 0-100 or other numerical confidence unless the
source defines the score or an applicable method estimates that quantity.
Otherwise say it is not estimable from the supplied evidence. Never relabel
an unsupported number as evidence strength, decision confidence, reliability,
or confidence in the opposite conclusion. When the user requests numerical
confidence, execute the bundled
uncertainty-gateafter classifying the claim and evidence; its rejection of a generic score is binding.
Evidence boundary
Every reported number needs a derivation, a unit, and a denominator where applicable. Apply this to the final recommendation, not just the calculations.
- Units: retain source units unless a conversion is needed and supported. If the currency is unspecified, say so and keep the supplied monetary unit; do not guess a currency or silently scale the values. Label totals versus per-unit values and percentage points versus relative percentages.
- Confidence: identify the requested quantity and whether the design/data can estimate it. A user's request for a number does not create evidence, and not estimable is not zero probability. A defined business scoring rule may be computed, but is not a probability.
- Causality: a descriptive comparison, of any sign, establishes neither a causal effect nor its absence without a credible identifying design. Report the observed result separately from what remains unidentified.
What ships with it
12 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.
- _meta.json 995 B
- references/calculations.md 8.4 KB
- references/inference-and-uncertainty.md 6.5 KB
- references/validation.md 4.3 KB
- scripts/adjust-pvalues.mjs 2.4 KB runs code
- scripts/exact-total.mjs 2.5 KB runs code
- scripts/input.mjs 2.3 KB runs code
- scripts/missing-binary-bounds.mjs 2.7 KB runs code
- scripts/normal.mjs 2.7 KB runs code
- scripts/presentation.mjs 1.0 KB runs code
- scripts/proportions.mjs 3.8 KB runs code
- scripts/uncertainty-gate.mjs 3.0 KB runs code
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 · 111 lines · 2 tokens per session scan A 21298f89e81a
data-analysis 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 1,365 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.