Evidence-graded pedagogy library, cognitive-load curriculum tree runtime, and interactive mastery assessment engine for AI tutoring agents.
Equip AI agents to teach complex technical subjects using Bloom's revised taxonomy, worked-example fading, spaced retrieval, Socratic diagnostic probes, and verifiable learner state machines.
Quickstart · What it makes · Install · How it works · Commands · Limits
When you ask a generic LLM to 'teach me X', it dumps a 2,000-word textbook summary that creates an illusion of competence without testing transfer or managing cognitive load. design-os-pedagogy gives AI agents a formal instructional design runtime grounded in cognitive science.
| Dimension | Generic AI / Manual Workflow | DESIGN:OS Agent Teacher (DESIGN:OS) |
|---|---|---|
| Instructional Flow | Passive 2,000-word wall of text with zero learner checks | Active worked-example fading, Socratic probes, and gated mastery nodes |
| Curriculum Structure | Flat bullet lists with hidden prerequisite gaps | Explicit DAG of prerequisite concepts and Bloom taxonomy target levels |
| Assessment Quality | Trivial recall trivia ('What does API stand for?') | Diagnostic misconception probes and near/far transfer challenges |
| Evidence Grading | Pop-psychology myths (e.g., VARK learning styles) | Strictly evidence-graded cognitive science (Sweller, Bjork, Roediger, Chi) |
| Privacy & Telemetry | Opaque cloud telemetry or unverified third-party APIs | Zero telemetry — 100% local execution (PRIVACY.md audited) |
In Claude Code:
/plugin marketplace add jangtrinh/design-os-pedagogy
/plugin install design-os-pedagogy@design-os-pedagogy
Or from your terminal (Codex, Gemini CLI, Antigravity, OpenCode, or standalone CLI):
git clone https://github.com/jangtrinh/design-os-pedagogy.git
cd design-os-pedagogy
python3 scripts/self_check.pyOpen your project in your AI coding agent and describe what you need:
"Design a 5-stage mastery curriculum tree for distributed consensus (Raft) with prerequisite DAGs and diagnostic transfer questions."
"Turn this codebase walkthrough into a worked-example fading sequence with interactive check-for-understanding probes."
"Audit our onboarding tutorial for cognitive load violations, missing prerequisite links, and passive wall-of-text explanations."
python3 scripts/self_check.pyEvery deliverable produced by design-os-pedagogy is backed by a deterministic verification gate rather than freehand AI guesswork.
Prompt: "Design a 5-stage mastery curriculum tree for distributed consensus (Raft) with prerequisite DAGs and diagnostic transfer questions."
| Deliverable / Mode | Best for | Output Format | Verification Gate |
|---|---|---|---|
| Curriculum DAG Specs | Decomposing a technical domain into prerequisite-ordered mastery nodes | JSON / Markdown Curriculum Tree |
DAG acyclicity & rubric check |
| Worked-Example Fading Loops | Transitioning learners from full examples -> partial completion -> independent problem solving | Interactive Lesson Prompts |
Cognitive-load gate PASS |
| Diagnostic Rubrics | Detecting specific mental-model bugs before advancing the learner | Structured Assessment Spec |
python3 scripts/self_check.py |
Choose the setup that matches your AI coding agent. Every option installs the same canonical skill (skills/design-os-pedagogy/SKILL.md) and /doctor diagnostic suite.
Run these two commands inside Claude Code:
/plugin marketplace add jangtrinh/design-os-pedagogy
/plugin install design-os-pedagogy@design-os-pedagogy
Install to your personal Codex skills directory:
git clone https://github.com/jangtrinh/design-os-pedagogy.git /tmp/design-os-pedagogy
mkdir -p ~/.codex/skills/design-os-pedagogy ~/.codex/prompts
cp -R /tmp/design-os-pedagogy/skills/design-os-pedagogy/* ~/.codex/skills/design-os-pedagogy/
cp /tmp/design-os-pedagogy/prompts/doctor.md ~/.codex/prompts/design-os-pedagogy-doctor.md
rm -rf /tmp/design-os-pedagogygit clone https://github.com/jangtrinh/design-os-pedagogy.git /tmp/design-os-pedagogy
mkdir -p ~/.gemini/skills/design-os-pedagogy
cp -R /tmp/design-os-pedagogy/skills/design-os-pedagogy/* ~/.gemini/skills/design-os-pedagogy/
rm -rf /tmp/design-os-pedagogygit clone https://github.com/jangtrinh/design-os-pedagogy.git /tmp/design-os-pedagogy
mkdir -p ~/.agents/skills/design-os-pedagogy
cp -R /tmp/design-os-pedagogy/skills/design-os-pedagogy/* ~/.agents/skills/design-os-pedagogy/
rm -rf /tmp/design-os-pedagogyVerify or uninstall
Verify installation:
python3 scripts/self_check.pyOr run /doctor inside Claude Code / Codex to inspect installed skill paths, plugin manifests, and gate health.
Uninstall:
rm -rf ~/.claude/skills/design-os-pedagogy ~/.codex/skills/design-os-pedagogy ~/.gemini/skills/design-os-pedagogy ~/.agents/skills/design-os-pedagogyOnce installed, skills/design-os-pedagogy/SKILL.md activates automatically when your prompt matches its domain triggers. Browse docs/cookbook.md for copy-paste prompt recipes.
Generate & Scaffold
"Design a 5-stage mastery curriculum tree for distributed consensus (Raft) with prerequisite DAGs and diagnostic transfer questions."
Audit & Verify
"Turn this codebase walkthrough into a worked-example fading sequence with interactive check-for-understanding probes."
Export & Automate
"Audit our onboarding tutorial for cognitive load violations, missing prerequisite links, and passive wall-of-text explanations."
| Command | Environment | What it does |
|---|---|---|
/doctor |
Claude Code / Codex | Read-only diagnostic check of installed skill paths, plugin manifests, and runtime prerequisites |
python3 scripts/self_check.py |
Terminal / CI | Deterministic offline verification of manifests, skill contracts, and governance files |
python3 scripts/self_check.py |
Terminal / CI | Verify pedagogy skill contracts, curriculum schema integrity, and repository delivery gates |
- Intent Routing — Your AI agent matches your request against
skills/design-os-pedagogy/SKILL.mdfrontmatter triggers. - Progressive Context Loading — Only the entry-point
SKILL.mdrouter loads initially; detailed recipes and scripts load on demand. - Deterministic Execution — Domain scripts and contracts execute locally with reproducible inputs and outputs.
- Gate Verification —
scripts/self_check.pyand domain verifiers (python3 scripts/self_check.py) validate the artifact before completion. - Zero-Telemetry Delivery — Verified files are written directly to your workspace with zero external network calls.
User Prompt / CLI Invocation
│
▼
┌───────────────────────────────────────────────┐
│ skills/design-os-pedagogy/SKILL.md
│ Progressive disclosure router & hard rules │
└───────────┬───────────────────────────────────┘
│ loads on demand
▼
┌───────────────────────────────────────────────┐
│ python3 scripts/self_check.py
│ Deterministic build & contract enforcement │
└───────────┬───────────────────────────────────┘
│ verifies
▼
┌───────────────────────────────────────────────┐
│ python3 scripts/self_check.py + /doctor │
│ Zero-telemetry local verification gate │
└───────────────────────────────────────────────┘
design-os-pedagogy uses progressive context disclosure so your agent's context window stays fast and focused:
| File | Loaded when |
|---|---|
skills/design-os-pedagogy/SKILL.md |
Always (~100–150 lines) — routing rules, triggers, and execution workflow |
docs/cookbook.md |
When selecting multi-step prompt recipes or domain patterns |
commands/doctor.md / prompts/doctor.md |
Only when running /doctor diagnostics |
llms.txt |
When indexed by AI answer engines, RAG pipelines, or repo crawlers |
design-os-pedagogy/
├── .claude-plugin/
│ ├── plugin.json # Claude Code plugin manifest
│ └── marketplace.json # Claude Code marketplace catalog
├── .codex-plugin/
│ └── plugin.json # OpenAI Codex plugin & interface manifest
├── .agents/
│ └── plugins/marketplace.json # Cross-agent local plugin registry
├── .factory-plugin/
│ ├── plugin.json # Factory / Droid plugin manifest
│ └── marketplace.json # Factory marketplace metadata
├── skills/
│ └── design-os-pedagogy/
│ └── SKILL.md # Canonical agent skill entrypoint
├── commands/
│ └── doctor.md # /doctor diagnostic slash command
├── prompts/
│ └── doctor.md # Codex diagnostic prompt mirror
├── scripts/
│ └── self_check.py # Deterministic repository & skill self-check
├── docs/
│ ├── cookbook.md # Copy-paste prompt recipes by job
│ └── llms.txt # GEO / LLM discovery index
├── PRIVACY.md # Zero-telemetry & local-first privacy commitment
├── SECURITY.md # Vulnerability disclosure & security policy
├── CONTRIBUTING.md # Contribution workflow & verification rules
├── CODE_OF_CONDUCT.md # Contributor Covenant code of conduct
├── CHANGELOG.md # Release history
├── llms.txt # Root LLM indexing manifest
├── LICENSE # PolyForm Shield 1.0.0
└── README.md
python3 scripts/self_check.pyprintsok: design-os-pedagogy self-check passed (design-os-pedagogy)and exits0.python3 scripts/self_check.pypasses with zero contract or test regressions.- Your AI coding agent loads
skills/design-os-pedagogy/SKILL.mdautomatically when given any prompt fromdocs/cookbook.md. - Network traffic during execution remains zero (guaranteed by
PRIVACY.md).
- Pure reference API lookups where an experienced engineer just wants a one-line CLI flag answer.
- Clinical, medical, or accredited K-12 compliance grading requiring licensed human oversight.
- Automated code generation where the user wants the task finished rather than explained.
design-os-pedagogy is one of the 13 source-available engines in the DESIGN:OS ecosystem:
- Contributing: See
CONTRIBUTING.mdfor pull request guidelines and verification gates (python3 scripts/self_check.py). - Code of Conduct: Governed by
CODE_OF_CONDUCT.md. - Security & Privacy: Zero telemetry — see
SECURITY.mdandPRIVACY.md. - Changelog & LLM Index: Track releases in
CHANGELOG.mdand machine-readable index inllms.txt. - License: PolyForm Shield 1.0.0 © Jang Trinh. Free to use and modify, including for paid client work; you may not resell it or build a competing product from it.
If design-os-pedagogy saves you time, a star on GitHub helps other engineers and AI agents find it.
