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 081c15ffbab4git 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/081c15ffbab4)<a href="https://agentmods.dev/skills/orkas-ai/orkas/081c15ffbab4"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/081c15ffbab4/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/081c15ffbab4"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/081c15ffbab4.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 | $0.01756 |
| Opus 5 | $0.00002 | $0.00878 |
| Sonnet 5 | $0.00001 | $0.00351 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
office-excel 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 11d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Office Excel
Tool Route
Use the bundled Office tools as the default artifact path. Do not install OfficeCLI, pandas, or openpyxl when the built-in tools cover the task.
- Use
read_fileswith onepathsitem for a broad workbook read; usemetadata_only:truewhen only prepared metadata is needed. - Use
create_xlsxfor a new.xlsx, including multiple sheets, live formulas, number formats, widths, common cell styling, and native editable charts in each sheet'schartsarray. Passpreview:falsewhen the requiredoffice_reviewwill provide the visual evidence. - Calling
create_xlsxis mandatory for a supported new workbook. Bash or local code may prepare input rows or perform calculations that the tool cannot express, but must not construct, rewrite, or patch the final.xlsxpackage. - Call
create_xlsxexactly once for one requested workbook. Include the complete initial workbook and chart plan in that call. If QA finds a correction, useoffice_readandedit_officeon the exact returned path; a file created in this conversation is refined in place. Do not restart with a secondcreate_xlsx, create a “可编辑” duplicate, or publish an intermediate workbook. - Use
office_readmode:"get"with onetargetsarray to batch-check representative formulas and computed/cached values;mode:"text"exposes displayed values, not formula definitions. - Use
edit_officefor.xlsx; it creates a separate working copy when the source was not already produced by this conversation. - After every create or edit, use
office_reviewwithaction:"check_and_render"when visible layout matters, oraction:"check"for structural-only validation. For a new workbook, reuse the sheet order supplied tocreate_xlsx; useoffice_readmode:"outline"when inspecting an existing workbook or after structural edits. Pass one-based worksheet positions inoffice_review.pages, never a worksheet name or cell range.
Artifact identity and convergence
- Treat the
artifact_pathin the latest create/edit<office-artifact>receipt as the only current artifact identity. Pass that exact path verbatim tooffice_read,office_review,edit_office, andpublish_outputs; do not reconstruct, shorten, or guess a path. - Batch all required worksheet pages into one review when possible. Do not repeat
office_reviewfor an unchangedartifact_revisionand the same page set; a page that failed to render may be retried once by itself. - Continue editing only when the latest review identifies a concrete blocking defect and a targeted repair. Consolidate related repairs into one edit batch, then review the new revision. When structure is valid and only warnings or subjective polish remain, stop editing and publish.
- If
publish_outputsreturnsE_OUTPUT_NOT_PRODUCED, do not edit, review, or regenerate the workbook. Retry publication once with an exacteligible_current_turn_pathsentry from the error. If no eligible path is returned or that retry fails, report the preserved artifact and the delivery blocker; never guess another path or claim publication succeeded.
What ships with it
1 file 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.
- 11d ago First seen · 58 lines · 3 tokens per session scan A 7c2d66bead6f
office-excel is a skill published in the GitHub repository Orkas-AI/Orkas (1,848 stars, last pushed yesterday), licensed MIT. It adds 3 tokens to every session and 1,756 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 2026-08-30.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
xlsx
Create/edit/analyze/verify spreadsheet workbooks including XLSX/CSV/TSV.
spreadsheets
Compatibility alias for the xlsx skill. Prefer loading xlsx.
sn-da-excel-workflow
A step-by-step workflow for analysing Excel workbooks with multiple sheets. It covers reading data, cleaning it, filtering and combining results, and exporting reports, with a separate strategy for large files.
sn-da-large-file-analysis
A workflow for analyzing very large Excel datasets, especially files with at least 10,000 rows. It uses lower-memory reading, streaming through rows, splitting work into chunks, and converting data to Parquet, a column-based data format suited to repeated analysis.
category-filtering-and-difficulty-analysis
A workflow for grouping Excel records into categories and analyzing them across several measures, including text length and terminology density.