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/anfaia/skillnet/agents-mdgit clone --depth 1 https://github.com/ANFAIA/SkillNetWhat 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 | $0.02251 | $0.02251 |
| Opus 5 | $0.01125 | $0.01125 |
| Sonnet 5 | $0.00450 | $0.00450 |
| Haiku 4.5 | $0.00225 | $0.00225 |
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.
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/
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.
- 2d ago First seen · 162 lines · 2,251 tokens per session scan A e30a91025f6e
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.
Other instructions, from other repositories
Clew CLAUDE.md
Instructions for miuuyy/Clew, covering claude.md, read first, product overview, core boundaries and engineering rules.
LLM-dev-demo AGENTS.md
Instructions for A3RDLab/LLM-dev-demo, covering agents.md, 仓库性质, 环境与密钥约定, 依赖管理 and 常用命令.
classroomio CLAUDE.md
Claude Code instructions for classroomio/classroomio, a project described as: The Open Source Education Platform for Companies. A Simple and Beautiful Alternative to Moodle LMS, EdX, Thinkific and Teachable.
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.
MoodleMCP CLAUDE.md
Claude Code instructions for leshamblin/MoodleMCP, covering claude instructions for moodle mcp server project, project context, key facts, critical safety information and current implementation.