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 deep-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/deep-research)<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/deep-research"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/deep-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/deep-research"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/deep-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 | $0.00186 | $0.03380 |
| Opus 5 | $0.00093 | $0.01690 |
| Sonnet 5 | $0.00037 | $0.00676 |
| Haiku 4.5 | $0.00019 | $0.00338 |
Grade A, and why
deep-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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The architecture is inspired by Stanford's STORM (perspective discovery + outline-first), Anthropic's multi-agent research system (parallel exploration + intelligent critique), and pi-autoresearch (living state files that survive context resets).
<Use_When>
- User wants DEEP understanding, not a quick summary
- Topic is complex, contested, or multi-faceted
- User needs to make a decision based on the research
- User wants to compare competing approaches with evidence
- User explicitly asks for /deep-research or "thorough research" </Use_When>
<Do_Not_Use_When>
- User wants a quick answer (use /research instead)
- User wants to find academic papers specifically (use /paper-discover)
- User wants to process an existing vault note (use /process)
- User wants cross-domain vault synthesis (use /synthesize) </Do_Not_Use_When>
Stage 0: SETUP
Parse $ARGUMENTS for the topic and optional depth flag:
--quick: faster, fewer rounds, sonnet everywhere, no perspective discovery--deep: more rounds, opus for critic and synthesis, outline reviewed by user- Default (no flag): balanced — perspective discovery, 2-4 rounds, opus for synthesis
Create the workspace:
TOPIC_SLUG=$(echo "$TOPIC" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | cut -c1-30)
WORK_DIR="temp/research-${TOPIC_SLUG}"
mkdir -p "$WORK_DIR"/{findings,gaps}
Resume check: Before creating, check if the workspace already exists:
ls "$WORK_DIR/state.md" 2>/dev/null
If state.md exists, read it and ask the user: "Found incomplete research on
[topic] (round N). Resume or start fresh?" If resuming, read state.md to
determine which stage to skip to.
Tell the user what's happening:
Deep researching "{topic}" ({depth mode}).
Setting up workspace at {WORK_DIR}...
What ships with it
6 files 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 · 376 lines · 186 tokens per session scan A 95cce44e8d2c
deep-research is a skill published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 186 tokens to every session and 3,380 once invoked, about $0.0009 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…