SkillNet AGENTS.md

A repository guide for SkillNet, a self-hosted learning system that creates and adapts courses from ideas or source material. It describes the application’s technologies, structure, and required startup path.

In plain words
What is it for?
Use it to start the project, understand its repository layout and technology choices, and work on adaptive courses, workspaces, authentication, or streaming responses.
Why use it?
It points contributors to the correct setup instructions and explains how the frontend, backend, database, authentication, and AI parts fit together.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/anfaia/skillnet/agents-md
Clone the repo
git clone --depth 1 https://github.com/ANFAIA/SkillNet

Made for: Codex, OpenCode.

Per session 2,251 This file is loaded in full into every session.
When invoked 2,251 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.02251 $0.02251
Opus 5 $0.01125 $0.01125
Sonnet 5 $0.00450 $0.00450
Haiku 4.5 $0.00225 $0.00225

Measured 2d ago against content hash e30a91025f6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SkillNet 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 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.

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.

AGENTS.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Asked to start the project? → RUNNING.md. Five steps, one decision (API key, local model, or neither), and it says what to verify afterwards. Do not reconstruct the commands from this file — the seed step is easy to miss and without it the dashboard is empty.

Project

SkillNet — open-source adaptive learning system. It creates courses from an idea or source material and can adapt their explanations, activities and interfaces to each person. Self-hosted, with organization and individual workspace modes.

Stack

Layer Technology
Frontend React 19 + Vite + Tailwind v4 + React Router + TanStack Query
Backend Python + FastAPI + fastapi-users
Database PostgreSQL + pgvector
Auth Session cookies (httpOnly, 7-day expiry) via fastapi-users CookieTransport
Real-time SSE (Server-Sent Events) for streaming LLM responses
AI orchestration LangGraph
LLM Any OpenAI-compatible API (user configures endpoint + key + model)
Deployment Docker Compose

Repo structure

skillnet/
├── AGENTS.md                         # This file (root instructions)
├── RUNNING.md                        # How to start the project — read this first
├── apps/
│   ├── skillnet-api/                 # FastAPI + LangGraph + pgvector (backend)
│   ├── skillnet-web/                 # React SPA (frontend)
│   │   └── AGENTS.md                 # Frontend-specific instructions
│   ├── skillnet-a2a/                 # A2A agent server (optional, `--profile a2a`)
│   └── skillnet-site/                # Public landing site
├── packages/
│   ├── a2tl-video/                   # A2TL-Video — compact spec for agent-generated video (TypeScript)
│   ├── a2tl-web/                     # A2TL-Web — compact spec for agent-generated web pages (TypeScript)
│   ├── mcp-md-reader/                # Markdown reader MCP server (TypeScript)
│   └── skillnet-mcp/                 # SkillNet MCP server — thin client of /ext/v1 (TypeScript)
├── docs/
│   ├── design/
│   │   ├── v1-scope.md               # What v1 is and isn't
│   │   ├── v2-dynamic-courses.md     # The v2 design (Spanish) — implemented, chosen per course
│   │   ├── ai-course-design.md       # Stateless AI endpoints and multi-model routing for course design (Spanish)
│   │   ├── openui-adoption.md        # Why OpenUI, and what its reactive layer would cost (Spanish)
│   │   ├── tuning.md                 # The dials for generation quality, and what each does
│   │   ├── course-packages.md        # A course as an installable directory (no LLM, no key)
│   │   ├── architecture.md           # Architecture decisions (decided + deferred)
│   │   ├── data-model.md             # PostgreSQL schema (v1 body + v2 appendix)
│   │   ├── screens.md                # Screen specs
│   │   └── design-system.md          # Visual design tokens and component patterns
│   └── research/                     # Investigation by topic
└── assets/

Read the full file on GitHub · 162 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.

  1. 2d ago First seen · 162 lines · 2,251 tokens per session scan A e30a91025f6e

Subscribe to this mod's changes

SkillNet AGENTS.md is an instructions file published in the GitHub repository ANFAIA/SkillNet (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,251 tokens to every session, about $0.0113 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.