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 tuan3w/obsidian-vault-agent --skill researchgit clone --depth 1 https://github.com/tuan3w/obsidian-vault-agentWrote 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/tuan3w/obsidian-vault-agent/research)<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/research"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/research/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/tuan3w/obsidian-vault-agent/research"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/research.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 | $0.00098 | $0.01681 |
| Opus 5 | $0.00049 | $0.00840 |
| Sonnet 5 | $0.00020 | $0.00336 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
research 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 10d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- User asks to research a topic ("research quantum error correction")
- User wants to understand something new ("what is RLHF and why does it matter?")
- User wants a research note created in the vault
- User uses /research with a topic </Use_When>
<Do_Not_Use_When>
- User wants to find academic papers specifically (use /paper-discover)
- User wants to process an existing vault note (use /process)
- User wants to synthesize across existing vault notes (use /synthesize)
- User has a YouTube video to process (use /youtube) </Do_Not_Use_When>
Stage 1: PLAN — Decompose the Question
Parse the topic from $ARGUMENTS. If vague, ask one clarifying question.
Break the research topic into 3-5 specific sub-questions that together cover the topic well. Think about:
- What IS it? (definition, core mechanism)
- Why does it matter? (motivation, impact, who cares)
- How does it work? (process, architecture, method)
- What are the tradeoffs? (limitations, alternatives, open problems)
- Where is it going? (trends, recent developments, future)
Present the sub-questions to the user briefly:
Researching "topic". Sub-questions:
1. ...
2. ...
3. ...
Searching now.
Don't wait for confirmation unless the topic is ambiguous — just show and go.
Stage 2: SEARCH VAULT — What Do We Already Know?
Before hitting the web, check what the vault already contains:
Grep(pattern="KEYWORD", path="notes/", glob="*.md", head_limit=15)
Also try MCP search if available:
mcp__obsidian-vault__search_notes(query="KEYWORD", limit=10)
Note any existing vault notes that are relevant — these become [[wikilinks]] in the output and inform what the web search should FOCUS on (gaps, not repeats).
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.
- 10d ago First seen · 208 lines · 98 tokens per session scan A 24aa2d801b23
research is a skill published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 98 tokens to every session and 1,681 once invoked, about $0.0005 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
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
fastmcp-client-cli
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
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…