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/kc0506/ntucool/ntucoolnpx skills add kc0506/ntucool --skill ntucoolgit clone --depth 1 https://github.com/kc0506/ntucoolWhat 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 | $0.00065 | $0.02792 |
| Opus 5 | $0.00032 | $0.01396 |
| Sonnet 5 | $0.00013 | $0.00558 |
| Haiku 4.5 | $0.00006 | $0.00279 |
Grade C, and why
ntucool scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Run the install step yourself (a single `curl … | sh`, see `commands/setup.md`), then have the user type `! cool login` (interactive — Bash tool can't drive the password prompt). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Run the install step yourself (a single `curl … | sh`, see `commands/setup.md`), then have the user type `! cool login` (interactive — Bash tool can't drive the password prompt). How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ntucool
NTU COOL is National Taiwan University's Canvas LMS instance at https://cool.ntu.edu.tw. This skill covers the cool CLI and its cool mcp MCP server, distributed at https://github.com/kc0506/ntucool.
Scope: NTU students working with their own enrolments — list/search courses, find PDFs, read assignments, check grades and submissions. Not for admins. Not for non-NTU Canvas instances (login is hardcoded to NTU's ADFS SAML SSO).
Setup gate — run BEFORE the first ntucool tool call
The plugin manifest can't install the cool binary or prompt for a password, so the first interaction in any session must verify setup. Do this once per conversation, before any ntucool tool/CLI call:
which cool 2>/dev/null && cool whoami 2>&1 | head -1
coolresolves to a path andwhoamireturns user info → setup OK, proceed.- Anything missing or
whoamierrors with 401 / "not logged in" / "command not found" → setup is incomplete. Drive the user through it before answering their original question.
The full setup procedure (install via prebuilt installer + cool login) is in the /ntucool:setup slash command. Either:
- Tell the user to run
/ntucool:setupand wait, OR - Run the install step yourself (a single
curl … | sh, seecommands/setup.md), then have the user type! cool login(interactive — Bash tool can't drive the password prompt).
After setup completes, resume the user's original task without making them re-ask.
Why the gate matters
The MCP server reads session.json + credentials.json written by cool login; there is no MCP login flow. If the session expires (cookies last ~24h), both CLI and MCP transparently re-login from saved credentials. If saved credentials are absent or stale, calls 401 deep inside the API client and surface as opaque tool errors. The gate catches that before you make the user wait through a failed tool call.
$HOME / sandbox mismatch is the rare third failure mode: cool login writes to the user's $HOME, but if Claude Code is running under a different user (sandbox, container), MCP won't see the session file. Confirm cool whoami works in the same shell environment the MCP server runs in.
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.
- 2d ago First seen · 154 lines · 65 tokens per session scan C c1412b7ea11d
ntucool is a skill published in the GitHub repository kc0506/ntucool (10 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 2,792 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…