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/tjmustard/hypergraph-coding-agent-framework/hyper-tutorial-runnpx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-tutorial-rungit clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-FrameworkWhat 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 | $0.00043 | $0.00883 |
| Opus 5 | $0.00022 | $0.00441 |
| Sonnet 5 | $0.00009 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
tutorial-run 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutorial Run
This skill reads any tutorial produced by /hyper-tutorial-generator and walks the user through it interactively — one section at a time, with in-context Q&A and on-demand access to code samples and supporting files.
When to use this skill
- When the user runs
/hyper-tutorial-runand wants to work through an existing tutorial. - When the user wants an interactive guided read (not a plain file open) of a
tutorials/<name>/folder.
How to use it
Step 0 — Choose a tutorial (HITL Gate #1)
List all subdirectories of tutorials/ (numbered). If the directory does not exist or is empty, inform the user and suggest running /hyper-tutorial-generator first.
Use AskUserQuestion to let the user select which tutorial to run. Wait for the selection before proceeding.
Step 1 — Load the tutorial
- Read
tutorials/<name>/tutorial.mdin full. - Extract the section headings to build a section list (use
##or###level headings). - Scan for available supporting subdirectories and note what's present:
code_samples/— runnable code examplesoutput_files/— expected outputsarchitecture_evolution/— diagrams and comparison tablesinput_files/— setup or example input files
- Display a brief ready message:
Ready to begin: <Tutorial Title>
Sections: N
Supporting files: code_samples/ (X files), output_files/ (Y files)
Let's start with Section 1.
Step 2 — Walk through sections (iterative HITL loop)
For each section in the tutorial:
-
Present the full section content as plain text (render markdown headers and lists).
-
Offer options via AskUserQuestion:
Section <N>/<Total>: <Section Title> Options: - Option A: Next section - Option B: I have a question about this section - Option C: Show me the code sample referenced in this sectionOnly show Option C if the section references a file in
code_samples/. -
Handle each response:
- Option A — move to the next section. If this was the last section, go to Step 3.
- Option B — answer the question using the tutorial content and your knowledge of the project. Do not move forward. Re-present the same section prompt after answering.
- Option C — identify the referenced
code_samples/file from the section text, read it in full, and display it. Then re-present the same section prompt.
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.
- yesterday First seen · 102 lines · 43 tokens per session scan A bc003d113eb0
tutorial-run is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 883 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后,主动执行此流程! 将学到的经验归档为 skill,供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.