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 IceWhaleTech/ZimaOS-Blue --skill researchgit clone --depth 1 https://github.com/IceWhaleTech/ZimaOS-BlueWrote 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/icewhaletech/zimaos-blue/research)<a href="https://agentmods.dev/skills/icewhaletech/zimaos-blue/research"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/research/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/icewhaletech/zimaos-blue/research"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/research.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 | $0.00027 | $0.01913 |
| Opus 5 | $0.00014 | $0.00957 |
| Sonnet 5 | $0.00005 | $0.00383 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
research 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 10d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
This document describes the unified Research family.
Research is one public surface with four execution modes:
mode=deep_research: citation-first, multi-source investigationmode=analyze: bounded synthesis over provided text, URLs, and/or search queriesmode=advisor: decision memo for selection, replacement, migration, and best-practice questionsmode=ui_review: UI/UX or accessibility review for a live URL or screenshot
How To Send
Use the canonical Research entry:
blue research query="ZimaOS-Blue research architecture" --json
Older prompts, wrappers, or internal routes may still refer to deep_research, analyze, or ui_reviewer. Treat those as compatibility aliases that now route to Research.
Routing Guide
| Need | Recommended mode | What it is best at |
|---|---|---|
| Multi-source research with evidence, citations, comparisons, or timeline work | deep_research |
Investigation with planning, retrieval, evidence merging, and confidence-backed answers |
| One synthesized report from known materials | analyze |
Bounded synthesis over provided text, URLs, and search queries |
| Decision support for technology choices or migration tradeoffs | advisor |
Recommendation memo with tradeoffs, risks, alternatives, and optional evidence |
| UI/UX, screenshot, or accessibility evaluation | ui_review |
Visual and accessibility review for URLs or images |
| Local workspace files or README inspection | Not this family | Prefer exec / file tools instead |
Common Parameters
action(optional):runorstatusquery(required for normal research runs unless another mode-specific input supplies the goal)mode(optional):auto,deep_research,analyze,advisor, orui_reviewlang(optional): output language such aszh-CNoren-USreport_style(optional): output style hint such assummary,timeline, or other mode-supported variants
Important:
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.
- 10d ago First seen · 212 lines · 27 tokens per session scan A a7927dbca368
research is a skill published in the GitHub repository IceWhaleTech/ZimaOS-Blue (25 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 1,913 once invoked, about $0.0001 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
video2knowledge
Convert videos into timestamped subtitles and structured knowledge artifacts. Two ingestion paths: (1) a native multimodal VLM (at most 4B params, via Ollama) reads sampled video frames into timestamped captions; (2) faster-whisper ASR transcribes the audio into timestamped subtitles. Then refine into a structured…
svelte-core-bestpractices
Guidance on writing fast, robust, modern Svelte code. Load this skill whenever in a Svelte project and asked to write/edit or analyze a Svelte component or module. Covers reactivity, event handling, styling, integration with libraries and more.
svelte-code-writer
CLI tools for Svelte 5 documentation lookup and code analysis. MUST be used whenever creating, editing or analyzing any Svelte component (.svelte) or Svelte module (.svelte.ts/.svelte.js). If possible, this skill should be executed within the svelte-file-editor agent for optimal results.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.