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 summarizegit 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/summarize)<a href="https://agentmods.dev/skills/icewhaletech/zimaos-blue/summarize"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/summarize/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/summarize"><img src="https://agentmods.dev/badge/skills/icewhaletech/zimaos-blue/summarize.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 | $0.00041 | $0.01001 |
| Opus 5 | $0.00020 | $0.00500 |
| Sonnet 5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
summarize 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize
Run the external summarize binary via blue exec.
Setup
Verify the CLI exists before relying on it:
blue exec command="summarize --help"
If needed, install it with Homebrew:
blue exec command="brew install steipete/tap/summarize"
Task Routing
| User Intent | Action |
|---|---|
| User explicitly asks for summarize.sh | blue exec command='summarize ...' |
| Need best-effort transcript extraction for a YouTube URL | blue exec command='summarize ... --youtube auto --extract-only' |
| Need a plain webpage/article summary and summarize.sh is not required | Prefer built-in web tools plus a normal answer |
| Need JS/login/interactive browsing first | Use the built-in browser tool / unified web tools first, then summarize the retrieved content |
When to use
Prefer this skill when the user asks any of:
- “use summarize.sh”
- “what’s this link/video about?”
- “summarize this URL/article”
- “transcribe this YouTube/video” (best-effort transcript extraction; no
yt-dlpneeded)
Command Usage
Quick summary:
blue exec command='summarize https://example.com --model google/gemini-3-flash-preview'
blue exec command='summarize /path/to/file.pdf --model google/gemini-3-flash-preview'
blue exec command='summarize https://youtu.be/dQw4w9WgXcQ --youtube auto'
YouTube: summary vs transcript
Best-effort transcript (URLs only):
blue exec command='summarize https://youtu.be/dQw4w9WgXcQ --youtube auto --extract-only'
If the user asked for a transcript but it’s huge, return a tight summary first, then ask which section/time range to expand.
Model + keys
Set the API key for your chosen provider:
- OpenAI:
OPENAI_API_KEY - Anthropic:
ANTHROPIC_API_KEY - xAI:
XAI_API_KEY - Google:
GEMINI_API_KEY(aliases:GOOGLE_GENERATIVE_AI_API_KEY,GOOGLE_API_KEY)
Default model is google/gemini-3-flash-preview if none is set.
Useful flags
--length short|medium|long|xl|xxl|<chars>--max-output-tokens <count>--extract-only(URLs only)--json(machine readable)--firecrawl auto|off|always(fallback extraction)--youtube auto(Apify fallback ifAPIFY_API_TOKENset)
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.
- 9d ago First seen · 134 lines · 41 tokens per session scan A e3e77bb7ee50
summarize is a skill published in the GitHub repository IceWhaleTech/ZimaOS-Blue (25 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,001 once invoked, about $0.0002 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.