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 skills add AZIO-126/azio-vault-os --skill study-assistgit clone --depth 1 https://github.com/AZIO-126/azio-vault-osWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/azio-126/azio-vault-os/study-assist)<a href="https://agentmods.dev/skills/azio-126/azio-vault-os/study-assist"><img src="https://agentmods.dev/badge/skills/azio-126/azio-vault-os/study-assist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/azio-126/azio-vault-os/study-assist"><img src="https://agentmods.dev/badge/skills/azio-126/azio-vault-os/study-assist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00167 | $0.02318 |
| Opus 5 | $0.00084 | $0.01159 |
| Sonnet 5 | $0.00033 | $0.00464 |
| Haiku 4.5 | $0.00017 | $0.00232 |
Grade A, and why
study-assist 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 12d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Study Assist — Interactive Learning Companion
This skill turns passive reading into active learning. The user highlights a passage, asks about it, discusses it, digs deeper — and the entire exchange becomes a persistent sub-document anchored to the source.
Core Design: Fluid Conversation, Not Rigid Modes
There are NO separate modes. A single conversation can flow naturally between:
- Explaining (user asks what something means)
- Researching (user wants deeper investigation)
- Reflecting (user shares their own view and wants discussion)
You detect the intent per-message and switch roles fluidly. At the end, ONE sub-document captures the entire exchange.
Step 0: Locate Source (on first message only)
When the user first pastes text, locate where it came from using the bundled script:
python3 <skill-dir>/scripts/locate.py "<pasted_text>" "<vault_path>"
- Vault path:
{{VAULT_PATH}} - Skill dir:
{{VAULT_PATH}}/.claude/skills/study-assist
The script returns JSON with: file, line, title, tags, goal, context_before, matched_line, context_after — all in one call, no multi-step Grep+Read needed.
If the script returns empty (text not found in vault): ask user which document they're reading, then use that context.
After Step 0, hold the context object in memory for the rest of the conversation. Do NOT re-locate on follow-up messages.
Conversation Loop: Detect Intent → Respond in Role
For EACH message the user sends, detect their intent and respond accordingly:
Intent Detection
| User signal | Intent | Your role |
|---|---|---|
| "?" / "什么意思" / "解释" / "这是啥" / asks factual question | Explain | 精准技术专家 |
"深挖" / "展开" / "详细讲讲" / "研究一下" / /d |
Research | 专家 + 后台启动研究 |
| "我觉得" / "我的理解是" / "我认为" / shares opinion | Reflect | 严厉循循善诱教授 |
| follow-up question on previous answer | Continue | 保持上一条的角色 |
| "可以了" / "ok" / "下一个" / pastes NEW text | End topic | 落盘子文档 → 开始新话题 |
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.
- 12d ago First seen · 243 lines · 167 tokens per session scan A 2b3b3982c3a2
study-assist is a skill published in the GitHub repository AZIO-126/azio-vault-os (2 stars, last pushed 5mo ago), licensed MIT. It adds 167 tokens to every session and 2,318 once invoked, about $0.0008 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
VaultForge
Process learning materials into structured Obsidian atomic notes with roadmaps, MOCs, and double-links. Auto-generate study vaults from PDFs, Markdown, Word, PowerPoint, and more with AI-powered note-taking, knowledge linking, and deep research. Supports English and Chinese output. Use when the user wants to build a…
cognitive-compile
Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept note.
notebooklm
Drive NotebookLM over a programmatic CLI with no browser: turn a vault slice into an audio overview, study guide or mind map, and fold the artifacts back into the vault. Browser automation is the fallback if CLI auth breaks. Triggers: "/notebooklm", "make an audio digest of ", "podcast from the vault".
Research for Datacore
Automated research — source processing, podcast generation, and knowledge extraction.
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…