researcher

researcher is an agent for coding agents from thoreinstein/obsidian-rag. It costs 36 tokens per session (370 once invoked), scanned A, original, MIT.

An agent for researching an Obsidian vault, a collection of linked notes, by combining meaning-based search, full-note reading, and following links between notes.

In plain words
What is it for?
Use it to investigate a topic, read the most relevant notes, trace connected material, check backlinks, and produce a cited synthesis.
Why use it?
It helps answer broad questions from multiple related notes while showing where the information came from and where the vault has gaps.

Agent

Part of the obsidian-rag plugin — 13 skills, 2 agents 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 agents/thoreinstein/obsidian-rag/researcher
Clone the repo
git clone --depth 1 https://github.com/thoreinstein/obsidian-rag

Or install obsidian-rag, the plugin that ships this one along with the rest of its 13 skills, 2 agents.

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 researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/thoreinstein/obsidian-rag/researcher.svg)](https://agentmods.dev/agents/thoreinstein/obsidian-rag/researcher)
Your own site
<a href="https://agentmods.dev/agents/thoreinstein/obsidian-rag/researcher"><img src="https://agentmods.dev/badge/agents/thoreinstein/obsidian-rag/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 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 $0.00036 $0.00370
Opus 5 $0.00018 $0.00185
Sonnet 5 $0.00007 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 4d ago against content hash bcf2ea02a4c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

researcher 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 4d 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.

agents/researcher.md · 38 lines

What it actually says

Vault research specialist for deep knowledge retrieval from the user's Obsidian vault.

Approach

  1. Semantic Search — Start with obsidian_rag_query to find the most relevant chunks
  2. Full Note Reading — Read the top-ranking notes in full for context
  3. Link Traversal — Follow [[wikilinks]] to find connected knowledge
  4. Backlink Discovery — Check what other notes reference key sources
  5. Synthesis — Combine findings with citations to specific notes

Guidelines

  • Always cite sources by note name: [[Note Name]]
  • If RAG returns empty, report that the vault may need indexing
  • For broad topics, run multiple queries with different phrasings
  • Prioritize recent notes when relevance scores are similar
  • Report gaps in the vault's knowledge honestly
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. 4d ago First seen · 38 lines · 36 tokens per session scan A bcf2ea02a4c3

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository thoreinstein/obsidian-rag (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 370 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.

Related

Other agents, from other repositories

fixer

Applies Codex code-review findings to the code tree: reads the cited issues, makes the minimum targeted fix per finding, runs relevant verification, and reports the structured result. Dispatch when a code-review artifact is ready to act on. Context: A Codex code-review artifact exists with cited findings. user: "Apply…

zeikar/hyperclaude · 274 tokens

planner

Decomposes a task into an ordered, bite-sized plan with file paths and per-step verification checks. Dispatch before starting non-trivial work whose steps aren't already obvious. Context: User is about to start multi-file, multi-step work. user: "Add OAuth2 login to the API." assistant: "I'll dispatch the planner…

zeikar/hyperclaude · 253 tokens

documenter

Edits one documentation file in-place to reflect code changes — minimal edits, no prose polish, no scope creep. Operates in UPDATE mode (file exists) or CREATE mode (file is new). Dispatched by /hyperclaude:hyper-docs-sync once per affected doc. Context: hyper-docs-sync identified a doc that needs updating after a…

zeikar/hyperclaude · 303 tokens

implementer

Executes one planned implementation step end-to-end: reads context, makes the minimum change, runs obvious verification, reports the diff. Dispatch when a concrete plan (from the planner or your own work) is ready to apply. Context: A plan exists and the next task is queued. user: "Run task 3 from the plan."…

zeikar/hyperclaude · 276 tokens

constitutional-validator

Validates specifications, plans, and implementations against the project constitution at .specify/memory/constitution.md.

zachjxyz/jvn · 25 tokens

security-auditor

Specialized sub-agent for security analysis with an isolated context window.

KhaiTrang1995/claude-code-structure · 0 tokens