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 agentmods add skills/cognis-digital/skillhub/summarizenpx skills add cognis-digital/skillhub --skill summarizegit clone --depth 1 https://github.com/cognis-digital/skillhubWrote 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/cognis-digital/skillhub/summarize)<a href="https://agentmods.dev/skills/cognis-digital/skillhub/summarize"><img src="https://agentmods.dev/badge/skills/cognis-digital/skillhub/summarize.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00115 |
| Opus 5 | $0.00008 | $0.00057 |
| Sonnet 5 | $0.00003 | $0.00023 |
| Haiku 4.5 | $0.00002 | $0.00012 |
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 4d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 18 lines · 16 tokens per session scan A fdbcf328cb61
summarize is a skill published in the GitHub repository cognis-digital/skillhub (0 stars, last pushed 2mo ago), with no licence file. It adds 16 tokens to every session and 115 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 2026-08-31.
Other skills, from other repositories
Content Summarizer
Fetch text from a URL or a memory key and produce a concise structured summary — a one-line headline, 3–7 key bullets, an approximate word count, and the source — then store it back in session memory. Use when the user says "summarize this", "give me the key points", "tl;dr", "summarize ", or "summarize the text…
text-statistics
Compute readability and structural statistics for a block of text: word count, sentence count, character count, average word length, and an approximate Flesch reading-ease score. Trigger when the user asks to analyze text, count words, measure readability, or get text statistics.
summarizer
Summarize URLs, PDFs, YouTube videos, and text content - extract key points and generate concise summaries.
text_summarizer
Summarizes long text into key bullet points.
add-or-fix-type-checking
Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs.
compromise-nlp
Write correct code with the compromise JavaScript NLP library (the npm package compromise, imported as nlp). Use this whenever you are writing or editing JS/TS that imports compromise, calls nlp(...), or chains methods like .match(), .tag(), .people(), .verbs(), .nouns(), .numbers(), .normalize(), or .replace() — and…