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 xg-gh-25/SwarmAI --skill s_summarizegit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_summarize)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_summarize"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_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/xg-gh-25/swarmai/s_summarize"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_summarize.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 | $0.00062 | $0.01943 |
| Opus 5 | $0.00031 | $0.00971 |
| Sonnet 5 | $0.00012 | $0.00389 |
| Haiku 4.5 | $0.00006 | $0.00194 |
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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize
Why? Get the essence of any content in seconds -- no need to read a 30-page doc, sit through a 2-hour transcript, or scroll through 200 Slack messages. Fast, structured, actionable summaries.
Quick Start
"Summarize this article: https://..."
"TL;DR this document" + file path
"Summarize the key points from this meeting transcript"
"What's this PDF about?" + file path
Input Types
| Input | How to Handle |
|---|---|
| URL / web page | Fetch with WebFetch, then summarize |
| Local file (.md, .txt, .pdf, .docx) | Read with Read tool or appropriate skill |
| Pasted text | Summarize directly |
| Multiple URLs/files | Summarize each, then synthesize |
| Clipboard content | Ask user to paste, or read from clipboard |
Workflow
Step 1: Identify Source and Length Target
Detect from user request:
| User Says | Length Target |
|---|---|
| "TL;DR" / "one liner" / "gist" | Ultra-short: 1-2 sentences |
| "summarize" / "key points" | Standard: 3-7 bullet points |
| "detailed summary" / "comprehensive" | Detailed: structured sections |
| "compare these" | Comparison: side-by-side analysis |
Default to Standard if not specified.
Step 2: Fetch Content
URLs:
Use WebFetch to retrieve and extract the page content.
Files:
Use Read tool for text/markdown.
Use s_pdf skill for PDF files.
Use s_docx skill for Word documents.
Use s_xlsx skill for spreadsheets.
Long content (>50K chars): Read in sections, summarize each section, then synthesize into a final summary.
Step 3: Analyze and Summarize
Extract these elements from the content:
| Element | Always Include? | Description |
|---|---|---|
| One-line summary | Yes | What is this about, in one sentence |
| Key points | Yes | 3-7 most important takeaways |
| Context/background | If relevant | Why this matters, what prompted it |
| Data/numbers | If present | Key metrics, stats, figures |
| Decisions/conclusions | If present | What was decided or concluded |
| Action items | If present | What needs to happen next |
| Open questions | If present | Unresolved issues |
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 · 303 lines · 62 tokens per session scan A e242b5ec80a8
summarize is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 1,943 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
prospect
Run a structured pre-mortem on a plan or approach BEFORE execution. Per-step risk enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, plan-formation diagnosis, action verdicts (PROCEED/SHRINK/SPLIT/DEFER/KILL)…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
papyrus-diagnose-compilation
Diagnose and fix LaTeX compilation failures. Use when the document does not compile, pdflatex/bibtex/biber/tectonic errors out, the PDF is stale, or the author reports a build/compile error in the Papyrus editor.
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
moai-docs-generation
Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.
document-converter
Convert documents bidirectionally via the pi-doc-engine facade: ingest PDF/DOCX/PPTX/XLSX to provenance-stamped Markdown (with OCR), and produce templated DOCX/PDF from Markdown with diagrams, TOC and round-trip merge. Use on "convert this PDF to markdown", "ingest these docs into kb", "make a DOCX from markdown with…