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/xujingchen1996/research-app-toolkit/school-selectnpx skills add xujingchen1996/research-app-toolkit --skill school-selectgit clone --depth 1 https://github.com/xujingchen1996/research-app-toolkitWrote 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/xujingchen1996/research-app-toolkit/school-select)<a href="https://agentmods.dev/skills/xujingchen1996/research-app-toolkit/school-select"><img src="https://agentmods.dev/badge/skills/xujingchen1996/research-app-toolkit/school-select.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 | $0.00057 | $0.00460 |
| Opus 5 | $0.00028 | $0.00230 |
| Sonnet 5 | $0.00011 | $0.00092 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
school-select 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.
What it actually says
School Selection Advice
Preconditions
- Read
../../memory.mdfirst. - If there is no application profile yet, prioritize suggesting CV analysis first, then do more credible school selection.
Language Rules
- Support three output modes:
zh,en, andbilingual. - If the user explicitly specifies the output language, prioritize the current request.
- Otherwise read
preferred_languagefrommemory.md. - If it is still unclear, follow the user's current conversation language.
- Proper nouns such as program names, department names, and official requirements may remain in the original language, but explanations and comparison conclusions should follow the selected language.
Fill In the Decision Variables First
If the user has not stated things clearly, fill in:
- target country / region
- degree type
- budget / funding requirements
- ranking preference
- enrollment time or application cycle
- research direction
Search Strategy
- Prioritize checking official program pages to confirm:
- program name
- admission requirements
- funding / scholarship
- deadline
- If the user cares about rankings, then additionally check the corresponding ranking source.
- Combine the user's background in
memory.mdto build three tiers:ReachMatchSafety
Output Requirements
- First provide a comparison table:
- school
- program
- tier
- deadline
- funding
- fit score
- Then provide detailed notes for each program:
- location
- key requirements
- fit judgment against the user's background
- faculty directions worth contacting
Constraints
- Application deadlines must be expressed as concrete dates; avoid vague expressions such as "this winter".
- If school requirements or funding information cannot be found, clearly write "to be verified".
- This is a high-cost decision category of advice, so prioritize current search results rather than memory.
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 · 64 lines · 57 tokens per session scan A ef0158cdd00d
school-select is a skill published in the GitHub repository xujingchen1996/research-app-toolkit (113 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 460 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
ark-documentation
Guidance for structuring Ark documentation using the Diataxis framework. Use this skill when creating new docs, deciding where content belongs, reviewing documentation PRs, or restructuring existing documentation.