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 instructions/vanderbilt-data-science/knowledge-spaces/claude-mdgit clone --depth 1 https://github.com/vanderbilt-data-science/knowledge-spacesWrote 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/vanderbilt-data-science/knowledge-spaces/claude-md)<a href="https://agentmods.dev/instructions/vanderbilt-data-science/knowledge-spaces/claude-md"><img src="https://agentmods.dev/badge/instructions/vanderbilt-data-science/knowledge-spaces/claude-md.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 | $0.01265 | $0.01265 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
knowledge-spaces 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Space Theory — Skill Suite
This project implements a suite of 10 Agent Skills that guide an AI agent through the full Knowledge Space Theory (KST) pipeline: from raw course materials to a usable knowledge graph that supports student assessment, adaptive instruction, and curriculum maintenance.
The skills follow the Agent Skills open standard and work across Claude Code, Codex, Cursor, GitHub Copilot, and other compatible platforms.
The suite supports both classical item-based KST and the newer Competence-Based KST (CbKST) framework (Heller & Stefanutti, 2024), which adds a latent skill/competence layer beneath observable items.
Skill Pipeline
Phase 1: Domain Analysis
- Extracting Knowledge Items (
/extracting-knowledge-items) — Extract atomic knowledge items from course materials - Decomposing Learning Objectives (
/decomposing-learning-objectives) — Decompose learning objectives into testable items using taxonomic frameworks (Bloom's, DOK, SOLO, Marzano's, Fink's) - Mapping Concepts and Competences (
/mapping-concepts-and-competences) — Build a concept map showing relationships between items; identify latent competences (CbKST)
Phase 2: Knowledge Structure Construction
- Building Surmise Relations (
/building-surmise-relations) — Construct the surmise relation (prerequisite quasi-order) via the QUERY algorithm, with CbKST competence relations - Constructing Knowledge Space (
/constructing-knowledge-space) — Derive the full knowledge space (states, fringes, learning paths) - Validating Knowledge Structure (
/validating-knowledge-structure) — Validate mathematical consistency, educational plausibility, and CbKST alignment
Phase 3: Application
- Assessing Knowledge State (
/assessing-knowledge-state) — Adaptive assessment of a student's knowledge state (BLIM/PoLIM) - Generating Learning Materials (
/generating-learning-materials) — Generate bespoke learning materials targeting a student's outer fringe (UDL 3.0 aligned) - Planning Adaptive Instruction (
/planning-adaptive-instruction) — JIT lecture/instruction planning from class-wide state analysis
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.
- 4d ago First seen · 86 lines · 1,265 tokens per session scan A a6588b8a75ba
knowledge-spaces CLAUDE.md is an instructions file published in the GitHub repository vanderbilt-data-science/knowledge-spaces (22 stars, last pushed 6mo ago), licensed MIT. It adds 1,265 tokens to every session, about $0.0063 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 instructions, from other repositories
education-agent-skills CLAUDE.md
Claude Code instructions for GarethManning/education-agent-skills, covering education agent skills library — claude code entry point, what this is, stack, test and read at session start.
education-agent-skills AGENTS.md
AGENTS.md instructions for GarethManning/education-agent-skills, covering agents.md — guidance for coding agents working on this repo, skill structure, conventions, test command and after adding or editing any skill.
claude-teacher-plugin CLAUDE.md
Claude Code instructions for yarikleto/claude-teacher-plugin, covering claude teacher plugin — developer guide, versioning, how to update the plugin (for users), repository structure and hook rules.
az104-cert-buddy copilot-instructions.md
Instructions for timothywarner-org/az104-cert-buddy, covering copilot instructions, repository purpose, key locations, skill and agent conventions and mcp server ids.
az104-cert-buddy CLAUDE.md
Instructions for timothywarner-org/az104-cert-buddy, covering claude.md, repository purpose, architecture, skill discovery (critical gotcha) and cross-reference dependencies.
skills CLAUDE.md
Claude Code instructions for ai-shifu/skills, a project described as: Skills for creating 1v1 interactive courses with AI-Shifu.