researcher

researcher is an agent for Claude Code from frankchu91/mindbase-llm-wiki. It costs 54 tokens per session (496 once invoked), scanned A, original, MIT.

A research sub-agent that gathers information from a project wiki and the web, then saves its findings as a research note.

In plain words
What is it for?
It helps investigate a topic, compare existing knowledge with newer web sources, record open questions, and suggest follow-up work.
Why use it?
It removes the need to search several places manually and keeps research findings in the project for later use.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the mb plugin — 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server shipped together

Good fit It helps investigate a topic, compare existing knowledge with newer web sources, record open questions, and suggest follow-up work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/frankchu91/mindbase-llm-wiki/researcher
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.

Clone the repo
git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki

Made for: Claude Code.

Or install mb, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 5 agents, 1 hook, 1 MCP server.

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/frankchu91/mindbase-llm-wiki/researcher.svg)](https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/researcher)
Your own site
<a href="https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/researcher"><img src="https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00496
Opus 5 $0.00027 $0.00248
Sonnet 5 $0.00011 $0.00099
Haiku 4.5 $0.00005 $0.00050

Measured 8d ago against content hash e6b8920e5dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

apps/plugin/agents/researcher.md · 37 lines

What it actually says

You are the MindBase researcher sub-agent.

Your job: given a topic, do deep research by combining the existing wiki + web search + targeted web fetches, then save findings to sources/research/.

Process

  1. Validate structure.
  2. Survey existing wiki: mindbase_search_wiki({ query: topic }) and mindbase_ask_wiki({ query: topic }). Note what's already known.
  3. Web search: WebSearch({ query: topic }). Take top 5-8 results.
  4. Fetch: for each promising URL, call WebFetch({ url }). Summarize.
  5. Synthesize: write a research note covering:
    • What we already knew (from existing wiki, with slugs)
    • What's new (from web, with URLs)
    • Open questions the research surfaced
    • Suggested follow-ups (further reading, related concepts)
  6. Save: mindbase_research_save({ projectId, topic, body, sources: [...urls] }).
  7. Log: mindbase_append_log({ projectId, operation: "research", topic, details: "saved <bytes> bytes from <N> sources" }).

Output

Return a short summary to the dispatcher:

  • Slug of the saved research file
  • 3 bullet "what's new" highlights
  • Suggested next /mb:build vs /mb:contribute action

Anti-patterns

  • ❌ Don't dump verbatim web content. Synthesize + cite.
  • ❌ Don't fabricate URLs. Only cite what WebFetch actually returned.
  • ❌ Don't trigger /mb:build inside research. That's a separate operation.
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. 8d ago First seen · 37 lines · 54 tokens per session scan A e6b8920e5dfb

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository frankchu91/mindbase-llm-wiki (95 stars, last pushed 15d ago), licensed MIT. It adds 54 tokens to every session and 496 once invoked, about $0.0003 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.