research

research is a command for coding agents from Michael-OvO/obsidian-knowledge-agent. It costs 14 tokens per session (298 once invoked), scanned A, original, MIT.

A web-research command that turns a topic into teaching notes with real sources. It adapts the notes to the structure and writing rules of an existing knowledge vault.

In plain words
What is it for?
Use it for focused questions or broad topics that need source-backed notes, linked concepts, runnable examples, diagrams, and citations.
Why use it?
It reduces the work of finding reliable references, explaining a topic clearly, and placing the result in the right vault location. It also records uncertainty and checks links.

Command

Part of the obsidian-knowledge plugin — 1 skill, 12 commands, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/michael-ovo/obsidian-knowledge-agent/research
Clone the repo
git clone --depth 1 https://github.com/Michael-OvO/obsidian-knowledge-agent

Or install obsidian-knowledge, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 2 hooks.

Wrote 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.

agentmods badge for research

README.md
[![agentmods](https://agentmods.dev/badge/commands/michael-ovo/obsidian-knowledge-agent/research.svg)](https://agentmods.dev/commands/michael-ovo/obsidian-knowledge-agent/research)
Your own site
<a href="https://agentmods.dev/commands/michael-ovo/obsidian-knowledge-agent/research"><img src="https://agentmods.dev/badge/commands/michael-ovo/obsidian-knowledge-agent/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00298
Opus 5 $0.00007 $0.00149
Sonnet 5 $0.00003 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 5d ago against content hash 0fc2d581776d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

plugins/obsidian-knowledge/commands/research.md · 21 lines

What it actually says

Research the topic in $ARGUMENTS and turn it into notes that teach.

  1. Recall + fit. Read .agents/learned/conventions.md if present and see how this vault is organized, so the result lands in the right place in the right shape.
  2. Research. Search the web and fetch authoritative sources — papers, official docs, primary references. Prefer primary/real sources over second-hand summaries, keep the URLs for citation, and note where sources disagree or are uncertain.
  3. Pick the altitude. A focused question → one strong note plus a source note. A broad topic → a small collection with an index, concept notes, and a concept-graph canvas if there are 3+ units. (See "Choose the altitude" in .agents/ingestion-workflow.md.)
  4. Write to the standard in .agents/style-guide.md: open from the real question; explain mechanism, assumptions, and limits; use the artifacts that genuinely teach (runnable code, an equation, a diagram); and cite sources in a Sources section with links.
  5. Wire & validate every wikilink, then reflect (journal entry + any durable lesson).
Changes

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.

  1. 5d ago First seen · 21 lines · 14 tokens per session scan A 0fc2d581776d

Subscribe to this mod's changes

research is a command published in the GitHub repository Michael-OvO/obsidian-knowledge-agent (206 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 298 once invoked, about $0.0001 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.