school-select

school-select is a skill for Claude Code from xujingchen1996/research-app-toolkit. It costs 57 tokens per session (460 once invoked), scanned A, original, MIT.

A guide for choosing schools and research programmes for applications, based on your background, budget, location, timeline, and research interests.

In plain words
What is it for?
Use it to compare PhD, MRes, and other research programmes and group options into reach, match, and safety choices. It can also check official programme details and rankings when relevant.
Why use it?
It reduces the work of comparing programmes and helps avoid recommendations that ignore funding, admission requirements, deadlines, or your academic profile.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the research-app-toolkit plugin — 9 skills, 9 commands, 1 agent, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/xujingchen1996/research-app-toolkit/school-select
Any agent
npx skills add xujingchen1996/research-app-toolkit --skill school-select
Clone the repo
git clone --depth 1 https://github.com/xujingchen1996/research-app-toolkit

Made for: Claude Code.

Or install research-app-toolkit, the plugin that ships this one along with the rest of its 9 skills, 9 commands, 1 agent, 1 hook.

Wrote 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.

agentmods badge for school-select

README.md
[![agentmods](https://agentmods.dev/badge/skills/xujingchen1996/research-app-toolkit/school-select.svg)](https://agentmods.dev/skills/xujingchen1996/research-app-toolkit/school-select)
Your own site
<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>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash ef0158cdd00d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

codex/skills/school-select/SKILL.md · 64 lines

What it actually says

School Selection Advice

Preconditions

  • Read ../../memory.md first.
  • 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, and bilingual.
  • If the user explicitly specifies the output language, prioritize the current request.
  • Otherwise read preferred_language from memory.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

  1. Prioritize checking official program pages to confirm:
    • program name
    • admission requirements
    • funding / scholarship
    • deadline
  2. If the user cares about rankings, then additionally check the corresponding ranking source.
  3. Combine the user's background in memory.md to build three tiers:
    • Reach
    • Match
    • Safety

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.
Changes

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.

  1. 6d ago First seen · 64 lines · 57 tokens per session scan A ef0158cdd00d

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories