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 qingxuantang/tar-engine --skill url-summarizegit clone --depth 1 https://github.com/qingxuantang/tar-engineWrote 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/qingxuantang/tar-engine/url-summarize)<a href="https://agentmods.dev/skills/qingxuantang/tar-engine/url-summarize"><img src="https://agentmods.dev/badge/skills/qingxuantang/tar-engine/url-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 5.1 | $0.00053 | $0.00426 |
| Opus 5 | $0.00026 | $0.00213 |
| Sonnet 5 | $0.00011 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
url-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 8d 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.
What it actually says
URL Summarize Skill
Fetch a webpage and return a one-paragraph summary of its content.
When to use
The user wish contains a URL (http:// or https://) AND asks for a summary, gist, or explanation of what the page contains. Examples:
- "summarize https://example.com"
- "what does https://en.wikipedia.org/wiki/AI_agent say?"
- "tell me about this page: https://blog.example.com/foo"
Execution
This skill uses a helper script to fetch the URL safely (with redirect handling and HTML text extraction). Steps:
- Extract the URL from the user's wish.
- Call the fetch script via
run_bash:
The script prints the page's text content to stdout (max 4000 chars).python3 scripts/fetch.py "<URL>" - Read the script's output.
- Generate a one-paragraph summary based on the text.
- Return the summary as the final response.
Style
- One paragraph, 3-5 sentences max.
- Focus on what the page actually says, not on the URL or technical details.
- If the page is empty, errors out, or has no readable text, say so plainly: "This page returned no extractable content."
What this skill demonstrates
This SKILL.md + scripts/ pattern is how Claude Code skills work when they need external data or computation. The SKILL.md is the entry point that the LLM reads. Scripts are invoked by the LLM via run_bash, not directly by the engine. This keeps the engine deterministic (it only reads SKILL.md and dispatches tool calls) while letting the LLM decide which scripts to call and with what args.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 48 lines · 53 tokens per session scan A 82faf22a88e9
url-summarize is a skill published in the GitHub repository qingxuantang/tar-engine (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 426 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 2026-08-31.
Other skills, from other repositories
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
skill-review
Critically review a workspace skill and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve a SKILL.md file or skill directory. Covers frontmatter validation, instruction clarity, completeness, and adherence to the Agent Skills Specification.
air-blackbox-sales-agent
AIR Blackbox's autonomous sales prospecting agent. Finds Python AI projects on GitHub that need EU AI Act compliance, identifies the right person to contact (CEO, CTO, lead maintainer), runs a free compliance scan, and drafts personalized outreach emails that convert to engagement. The sales flow: free scan as the…
interpret-results
Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.
compliance-scan
Scans a Python AI project for EU AI Act compliance gaps using AIR Blackbox. Use when the user asks to check compliance, scan their code, audit their AI project, or mentions EU AI Act, Articles 9-15, or compliance checking.
skill-scorer
A review tool for Agent Skills, which are instruction files that guide coding agents. It supports skills made for Cursor, Claude, and OpenClaw.