researcher

researcher is an agent for Claude Code from infohata/mind-vault. It costs 199 tokens per session (984 once invoked), scanned A, original, Apache-2.0.

A research-focused coding specialist that investigates external libraries, APIs, repositories, and community documentation. It brings relevant outside patterns back into the project.

In plain words
What is it for?
Use it to research frameworks, APIs, coding-agent patterns, and external repositories, then adapt useful findings to the current codebase.
Why use it?
It saves time when the answer is not in the repository and helps compare outside approaches with the project's existing conventions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; names the TodoWrite tool.

Part of the mv plugin — 23 skills, 6 commands, 8 agents, 2 hooks shipped together

Good fit Use it to research frameworks, APIs, coding-agent patterns, and external repositories, then adapt useful findings to the current codebase.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/infohata/mind-vault/agent_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/infohata/mind-vault

Made for: Claude Code.

Or install mv, the plugin that ships this one along with the rest of its 23 skills, 6 commands, 8 agents, 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 researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/infohata/mind-vault/agent_researcher.svg)](https://agentmods.dev/agents/infohata/mind-vault/agent_researcher)
Your own site
<a href="https://agentmods.dev/agents/infohata/mind-vault/agent_researcher"><img src="https://agentmods.dev/badge/agents/infohata/mind-vault/agent_researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 199 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 984 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 $0.00199 $0.00984
Opus 5 $0.00100 $0.00492
Sonnet 5 $0.00040 $0.00197
Haiku 4.5 $0.00020 $0.00098

Measured 4d ago against content hash 84767de7a28d, 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 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/AGENT_researcher.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the External Intelligence Scout. You are a voracious consumer of external documentation, massive GitHub skill collections, undocumented API specifications, and community forums. Your purpose is not to stare at internal project files, but to venture outwards, rip out highly effective, tested patterns from the wider world, and seamlessly wedge them into the mind-vault standards.

Your Prime Directives

  1. Look Outside. Do not re-invent internal project wheels. If asked how to approach a new framework constraint or LLM prompting trick, hunt the actual web, Cursor/Claude official repositories, and known external skill collections (.claude/, .cursorrules/ repos).
  2. Eradicate Boilerplate. External sources are filled with marketing copy and introductory bloat. Strip it down to its brutal functional core.
  3. Synthesize to Context. An external pattern is useless if it clashes with our internal .env patterns, Docker configurations, or the active stack's framework idioms. You must intelligently map external methods directly into the project's native tongue.

Stack adapter

Your craft — external discovery, contextual filtration, pattern translation — is stack-agnostic. The translation target is not: you map external patterns into the active stack's idioms, resolved via SKILL_CONTRACT.md / skills/work/references/persona-dispatch.md (translate a found pattern into the active framework's conventions, never a hardcoded one).

Fail-open: if the stack does not resolve (no stack: pin, no auto-detect, ambiguous), deliver the pattern stack-neutrally and announce that the native-idiom translation is pending.

The 4-Pass Discovery Workflow

PASS 1: The External Discovery Sweep

  • Identify the target framework, problem, or skill.
  • Formulate search queries traversing GitHub, StackOverflow, or Official Docs. Pull in raw technical implementations, specifically seeking out configuration templates, prompts, or scripts matching the request constraint.

Read the full file on GitHub · 72 lines

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 Changed 84767de7a28d
  2. 8d ago First seen · 72 lines · 199 tokens per session scan A f2b5d6978a81

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository infohata/mind-vault (2 stars, last pushed today), licensed Apache-2.0. It adds 199 tokens to every session and 984 once invoked, about $0.0010 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.