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 skills/aayushostwal/nexus/tutorialnpx skills add aayushostwal/nexus --skill tutorialgit clone --depth 1 https://github.com/aayushostwal/nexusWhat 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 | $0.00064 | $0.01376 |
| Opus 5 | $0.00032 | $0.00688 |
| Sonnet 5 | $0.00013 | $0.00275 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
nexus-tutorial 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutorial Generation Protocol
Produce complete, executable Jupyter Notebooks that work on the first run.
Compatibility
- Language: Python 3.10+
- Output:
.ipynbfile +Makefile - Style: PEP 8, GitHub-renderable Markdown, clean saved outputs
Workflow
Step 1 — Reproducibility Block
Begin every notebook with:
- Shell commands cell:
python -m venv .venv && source .venv/bin/activate pip installcell with all required libraries (pin versions:langchain==0.2.0)- Kernel check instructions as a Markdown cell
Makefilewithmake jupytertarget and Python version pin (e.g..python-versionfile)
Step 2 — Production-Ready Configuration
- Create a Pydantic
BaseSettingsclass to validate all environment variables on startup - Load secrets with
python-dotenv; raise an explicitValueErrorwith a helpful message if a key is missing - Document every production failure mode: missing keys, rate limits, model errors, network timeouts
Step 3 — Structural Outline
Create Markdown cells with headers H1–H3:
- H1 — Title: What the tutorial builds in one sentence
- H2 — Objective: One paragraph "what you will build and why"
- H2 — Prerequisites: List exact API keys, GPU requirements, or account setup steps
- H2 — Architecture Diagram: Mermaid diagram showing end-to-end system flow
Step 4 — Code Implementation
Rules for every code cell:
- Self-contained or explicitly references previously defined variables
- Python type hints on all function signatures
- Comments explain why — not what (bad:
# create list, good:# dedup before sending to avoid API double-charge) - One concept per cell; max ~30 lines per cell — split into functions if longer
- Never hardcode credentials; always use
settings.api_keyfrom the Pydantic config
Step 5 — Explanatory Narrative
Between every pair of code cells, add a Markdown cell that:
- States the "why" behind the implementation choice (e.g., "We use a ReAct loop here because it lets the agent decide when to call tools vs. answer directly")
- Describes the expected output when the cell runs
- Lists one or two common errors with their fixes (e.g., "RateLimitError → add
time.sleep(1)between calls")
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 132 lines · 64 tokens per session scan A 1bc56890c63d
nexus-tutorial is a skill published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 1,376 once invoked, about $0.0003 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 skills, from other repositories
cangjie-skill
Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into skills" — i.e. wants the frameworks, principles, and methodologies in long-form content…
productize-yourself
当用户在纠结职业/副业/自由职业方向、问「我该做什么才能赚钱/不被替代」、或想找到自己的独特优势时调用。 核心理念: 特殊知识(不可培训、对你像玩对别人像工作) × 产品化(杠杆规模化) = 无可替代的致富定位。 不适用于: 纯求职投递、写简历、已有明确方向的执行细节。 Triggers: 找方向/独特优势/副业/不可替代/productize/special knowledge/moat.
飞书多 Agent 配置助手
交互式引导配置多 Agent 系统,支持批量创建、凭证验证、角色模板.
prysai-adversarial-project-review
Review an LLM learning product, documentation site, Skill library, or candidate release from the strongest plausible opposing case. Use when deciding whether a project is genuinely useful, safe, teachable, maintainable, or ready to publish; when a team asks for a professor, scientist, practitioner, or open-source…
prysai-field-signal-curator
Convert public forum posts, issues, support discussions, interviews, or repeated user questions into a traceable demand and failure-signal record. Use when deciding what an LLM tutorial, platform adapter, Lab, FAQ, or application playbook should teach. Do not use community reports to prove a root cause, official…
prysai-platform-adapter-review
Audit a proposed tutorial or workflow for Codex, Claude Code, Grok, ChatGPT, Gemini, Copilot, or another LLM platform against a platform-adapter contract. Use when deciding whether platform-specific content adds a sourced, runnable, maintainable delta from the universal LLM core. Do not use for a general model ranking…