What is AcadeMong CLAUDE.md?

A project specification and build guide for AcadeMong, an application that helps Thai students choose eligible university programmes under Thailand’s TCAS admissions system. It defines the project’s goals, technology, architecture, and rules for handling admissions data.

Use it when building or changing AcadeMong, especially its eligibility checks, university and major recommendations, career guidance, and Thai-language student support.

It gives developers one shared reference for how the application should work and prevents an AI model from making up eligibility requirements that must come from the database.

How Khronossu/AcadeMong configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Khronossu/AcadeMong. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Khronossu/AcadeMong/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Khronossu/AcadeMong

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/khronossu/academong/claude-md/github.svg)](https://agentmods.dev/instructions/khronossu/academong/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/khronossu/academong/claude-md"><img src="https://agentmods.dev/badge/instructions/khronossu/academong/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/khronossu/academong/claude-md"><img src="https://agentmods.dev/badge/instructions/khronossu/academong/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11,781 This file is loaded in full into every session.

When invoked 11,781 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.11781	$0.11781
Opus 5.5	$0.04712	$0.04712
Sonnet 5.5	$0.02356	$0.02356
Haiku 4.5	$0.01178	$0.01178

Measured 2mo ago against content hash 8e7e298d36c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AcadeMong CLAUDE.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 2mo 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.

CLAUDE.md · 1,099 lines

How it starts

The opening of the file, as written. The whole thing — 1,099 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AcadeMong: Project Specification & Build Guide

This document is the single source of truth for the AcadeMong project. Scope: Production-grade system. Phases 1–11 cover the core build; Phases 12–13 cover production deployment and feedback automation. All team members must read this before writing a single line of code.

1. Project Overview

An adaptive AI decision-support system for Thai students applying to universities under the TCAS system. Combines deterministic eligibility validation, hybrid RAG-based advisory, personalized major recommendations, and career path guidance.

Key constraint: The system must never hallucinate eligibility criteria (GPAX minimums, subject requirements). These always come from SQL — never from an LLM.

Target users: Thai high school students (primarily Thai-language queries).

Target universities (initial): Chulalongkorn, Mahidol, Kasetsart, Thammasat, Srinakharinwirot.

2. Goals

Help students identify which majors/universities they are eligible for
Recommend majors aligned to their academic profile and interests
Guide career path planning with major → career → salary → license mapping
Retain user memory across sessions for personalized longitudinal guidance
Run entirely locally via Docker (no mandatory external API dependency)

3. Tech Stack

Layer	Technology	Reason
Backend	FastAPI (Python)	Async, lightweight, easy to structure
Primary LLM	`scb10x/llama3.1-typhoon2-8b-instruct` (Ollama)	Thai language capable, runs locally
Fallback LLM	Gemma 3/4 (8B) — pending Phase 2.5 eval vs Llama3.1:8b	See §7.2
Embeddings	`nomic-embed-text` (Ollama)	Local, no API cost
Reranker	`bge-reranker-base` (cross-encoder)	RAG Phase 6 reranking
Safety classifier	Llama Guard 3 (1B)	Output safety filter, Phase 9.5
Vector DB	Qdrant	RAG retrieval, Docker-native
Relational DB	PostgreSQL 16	Structured eligibility data + user memory
Session Cache	Redis 7	Short-term session memory
Auth	Firebase (Google OAuth + Email/Password)	idToken verified by `firebase-admin`
Frontend	React (single page)	Chat UI + profile form + career view
Containerization	Docker Compose (dev) / ECS + RunPod (prod)	See §18

Read the full file on GitHub · 1,099 lines

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.

2mo ago First seen · 1,099 lines · 11,781 tokens per session scan A 8e7e298d36c4

Subscribe to this mod's changes

AcadeMong CLAUDE.md is an instructions file published in the GitHub repository Khronossu/AcadeMong (2 stars, last pushed 5mo ago), licensed MIT. It adds 11,781 tokens to every session, about $0.0471 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 2026-08-31.

AcadeMong CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AcadeMong CLAUDE.mdKhronossu/AcadeMong	Instructions file	2	5mo ago	MIT	A	11,781	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

AcadeMong: Instructions file for Claude Code