Borrowing it
Nothing to install: this file belongs to yyu0310/nccu-course-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yyu0310/nccu-course-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/yyu0310/nccu-course-mcpWrote 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/instructions/yyu0310/nccu-course-mcp/agents-md)<a href="https://agentmods.dev/instructions/yyu0310/nccu-course-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yyu0310/nccu-course-mcp/agents-md/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/instructions/yyu0310/nccu-course-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yyu0310/nccu-course-mcp/agents-md.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 | $0.00826 | $0.00826 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
nccu-course-mcp AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — NCCU Course MCP
Context for AI assistants working on this repo.
What this is
A local (stdio) MCP server that queries NCCU's course-listing API
(es.nccu.edu.tw, backing qrysub.nccu.edu.tw) and exposes five tools:
search_all, check_schedule, list_departments, search_courses,
get_syllabus. Live-only: no local course database.
Design principle: sink model intelligence into deterministic code (structured
slots, note_facts mining, conflict checking) so weak models get the same
answer quality as strong ones. Tool docstrings carry the query guide; they are
the only documentation every MCP client is guaranteed to see. NEVER build a
docstring by string concatenation ("""...""" + X): it silently becomes
__doc__ = None and the tool registers with no description (test 6g guards this).
Layout
src/nccu_course_mcp/server.py— FastMCP entry (main()), the five tools, dept resolution.src/nccu_course_mcp/client.py— legacy-TLS HTTP session,search_raw(),normalize(),fetch_syllabus().src/nccu_course_mcp/dept_codes.json— department code↔name snapshot (loaded at import).src/nccu_course_mcp/build_dept_codes.py— regenerate the snapshot by scanning live.src/nccu_course_mcp/test_server.py— functional self-test (hits live API).
Run / test
python -m venv .venv && ./.venv/bin/pip install -e .
./.venv/bin/python src/nccu_course_mcp/test_server.py
Gotchas (don't undo these)
- Legacy TLS: the upstream needs
OP_LEGACY_SERVER_CONNECT; Python's default SSL rejects it. The adapter inclient.pyhandles it; keep it. - 500-row cap: broad queries (omitting
dp3) are truncated at 500 rows upstream. Always query per department (dp3), never school-wide in one call. - Query shape:
sem+dp3is enough;dp1/dp2are optional. For regular departments,dp3= first 3 digits of a course id = the department code. - dp3 is NOT always the course-id prefix (2026-07-17 bug): school-wide units use
their own dp3 code spaces: 整開/通識 (107=經濟學, 2S4=社會科學類通識; course ids start
000), 學分學程 (P01–P79), 體育/國防 (6S1/7S1), plus alphanumeric college codes (ZU1, ZC0, NU1, 1T3…). The authoritative code tree is the qrysub frontend static filehttps://qrysub.nccu.edu.tw/assets/api/unit.json(17 L1 units / L2 level / L3 = dp3).build_dept_codes.pyscans that whole tree; the hardcoded NAME dict is fallback only. - Same name, two codes: a department name can map to both an undergrad and a
graduate code (e.g. 財務管理學系 = 307 and 357).
_resolve_deptrefuses to guess. fetch_syllabusis host-restricted to*.nccu.edu.tw; keep that check (trust boundary).
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 · 56 lines · 826 tokens per session scan A a6ea4ac314f8
nccu-course-mcp AGENTS.md is an instructions file published in the GitHub repository yyu0310/nccu-course-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 826 tokens to every session, about $0.0041 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.