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/allens0104/skill-browser/content-summarynpx skills add AllenS0104/skill-browser --skill content-summarygit clone --depth 1 https://github.com/AllenS0104/skill-browserWrote 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/allens0104/skill-browser/content-summary)<a href="https://agentmods.dev/skills/allens0104/skill-browser/content-summary"><img src="https://agentmods.dev/badge/skills/allens0104/skill-browser/content-summary.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 5.1 | $0.00032 | $0.00522 |
| Opus 5 | $0.00016 | $0.00261 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
content-summary 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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content summary skill
This is the short public alias for:
content-search-summarization
Also available as simpler aliases:
summary内容摘要
Use this skill when you want to:
- search Bilibili, YouTube, or similar public content platforms
- pick the top N relevant results for a topic
- summarize each item in Chinese with links
Primary guidance
- Prefer
openclifor supported platforms. - If
opencliis unavailable, fall back to Playwright scraping of public result pages. - Rank by relevance first, popularity second.
- Open selected result pages and use metadata to improve summaries.
- Use a structured output with source, capture time, link, summary, and confidence.
Key rules
- Always include source links.
- Include capture time or say when the timestamp is not visible.
- Do not pretend a full video was watched if only metadata was collected.
- Phrase summaries conservatively when based on public page metadata.
- Add a confidence label and a short caveat when the summary is metadata-based.
Quick invocation template
You do not need to use only /content-summary.
Reliable invocation patterns include:
/content-summaryuse the content-summary skill- a natural-language request that clearly asks for content search, ranking, and summary output
Use prompts like:
Use /content-summary to find the top 5 results for <topic> on <platform> and summarize each item with links and confidence labels.
使用 /content-summary 在 <平台> 搜索 <主题>，筛选 Top 5，并输出带链接与置信度的摘要。
Please find the top results for <topic> on <platform>, rank them by relevance, and summarize each item with links and confidence notes.
Output contract
The skill output should always include:
- search method used (
openclior fallback) - keyword and capture scope
- ranked results with links
- per-item confidence and caveat
- explicit note when summaries are metadata-inferred
Pointer
For the full detailed playbook, also see:
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.
- 6d ago First seen · 79 lines · 32 tokens per session scan A 8627b40d7bd1
content-summary is a skill published in the GitHub repository AllenS0104/skill-browser (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 522 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 2026-08-31.
Other skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
azure-resource-manager-mysql-dotnet
Azure MySQL Flexible Server SDK for .NET. Database management for MySQL Flexible Server deployments.
idor-testing
Provide systematic methodologies for identifying and exploiting Insecure Direct Object Reference (IDOR) vulnerabilities in web applications.
aws-security-audit
Comprehensive AWS security posture assessment using AWS CLI and security best practices.
claimable-postgres
Provision instant temporary Postgres databases via Claimable Postgres by Neon (pg.new). No login or credit card required. Use for quick Postgres environments and throwaway DATABASEURL for prototyping.
gha-security-review
Find exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST include a concrete exploitation scenario — if you can't build the attack, don't report it.