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 somnus0x/agt-skill-pack --skill link-triagegit clone --depth 1 https://github.com/somnus0x/agt-skill-packWrote 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/somnus0x/agt-skill-pack/link-triage)<a href="https://agentmods.dev/skills/somnus0x/agt-skill-pack/link-triage"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/link-triage/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/somnus0x/agt-skill-pack/link-triage"><img src="https://agentmods.dev/badge/skills/somnus0x/agt-skill-pack/link-triage.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 | $0.00043 | $0.00759 |
| Opus 5.5 | $0.00017 | $0.00304 |
| Sonnet 5.5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
link-triage 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Link Triage — AI Reads So You Don't Have To
You save 30 links a day. You read maybe 2. The rest rot in bookmarks until you forget they exist.
Link Triage turns any URL into a 3-5 line summary with key takeaways, category, and relevance score — so you know what's worth your time without reading the full thing.
Setup
Drop-in prompt (copy into your AI tool):
เมื่อผมส่ง URL มา ให้:
1. อ่านเนื้อหาทั้งหมด
2. สรุปเป็น 3-5 bullet points เน้น key takeaway
3. จัดหมวดหมู่ (tech, business, personal, research)
4. ให้คะแนน relevance 1-5 ว่าเกี่ยวกับงานที่ทำอยู่แค่ไหน
5. ถ้า relevance 4-5 บอกว่าเกี่ยวยังไงและควรอ่านเต็มไหม
English version:
When I send a URL:
1. Read the full content
2. Summarize in 3-5 bullet points focusing on key takeaways
3. Categorize (tech, business, personal, research)
4. Score relevance 1-5 for how related it is to my current work
5. If relevance 4-5, explain why and whether I should read the full article
What it handles
Works with any content type your AI can access:
- Articles & blogs — extract and summarize
- Tweets & threads — pull full thread, summarize the argument
- YouTube videos — transcript extraction → summary
- GitHub repos — README + structure → what it does, why it matters
- PDFs & research papers — extract key findings
- Newsletters — pull the 2-3 items that matter
Add to your CLAUDE.md
### Link triage
When I send a URL, automatically read the content, summarize in 3-5 bullets,
categorize, and score relevance 1-5 to my current work.
If relevance is 4+, explain why I should care.
Building a reading queue (optional)
If you want to track what you've read and what's pending:
เก็บ log ของทุกลิงก์ที่ส่งมาใน reading-queue.md
แต่ละ entry มี: title, URL, summary, category, relevance score, status (unread/read/archived)
เรียงตาม relevance สูงสุดก่อน
This gives you a persistent, searchable reading queue that you can review weekly.
When to use
- Someone sends you a link in chat — triage it before deciding to read
- You're catching up on newsletters — batch triage 10 links in 2 minutes
- You found an interesting thread at midnight — save and triage, read tomorrow
- Weekly reading review — scan your queue, archive what's stale
What ships with it
2 files 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.
- 1mo ago First seen · 83 lines · 43 tokens per session scan A 2adff8e0accc
link-triage is a skill published in the GitHub repository somnus0x/agt-skill-pack (74 stars, last pushed 18d ago), licensed Apache-2.0. It adds 43 tokens to every session and 759 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…