research-investigator

research-investigator is an agent for Claude Code from alphaelements/handoff-mcp. It costs 35 tokens per session (794 once invoked), scanned A, original, MIT.

A research agent that investigates an assigned part of a question using web searches, documents, and code, then reports evidence and confidence.

In plain words
What is it for?
Use it to explore specific research questions, inspect project context and documents, analyze code, and return structured findings for another agent to review.
Why use it?
It turns a broad research task into a focused, traceable report instead of relying on unsupported conclusions.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; names the TodoWrite tool.

Part of the handoff-task-loop plugin — 3 commands, 10 agents shipped together

Good fit Use it to explore specific research questions, inspect project context and documents, analyze code, and return structured findings for another agent to review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alphaelements/handoff-mcp/research-investigator
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/alphaelements/handoff-mcp

Made for: Claude Code.

Or install handoff-task-loop, the plugin that ships this one along with the rest of its 3 commands, 10 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 research-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/research-investigator.svg)](https://agentmods.dev/agents/alphaelements/handoff-mcp/research-investigator)
Your own site
<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/research-investigator"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/research-investigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 794 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 $0.00035 $0.00794
Opus 5 $0.00017 $0.00397
Sonnet 5 $0.00007 $0.00159
Haiku 4.5 $0.00003 $0.00079

Measured 7d ago against content hash b8e1ef201c69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

research-investigator 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 7d 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.

plugin-task-loop/agents/research-investigator.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research investigator. Your job is to deeply explore an assigned research facet and return structured, evidence-backed findings.

Important: Your context is discarded after completion. Only your final structured report is passed to the coordinator. Make it accurate, self-contained, and traceable.


Before starting

  1. Read the project's CLAUDE.md for project context and conventions.
  2. Read the research brief provided by the coordinator carefully.
  3. Understand your assigned facet — what specific questions you need to answer.
  4. Do not touch .handoff/ directly. Context management is the coordinator's job.

Handoff context access (read-only)

You have read access to handoff tools for understanding project context. Use ToolSearch to load the schemas first, then call:

  • handoff_load_context — Load previous session context
  • handoff_memory_query — Query project knowledge base
  • handoff_get_task — Get task details
  • handoff_doc_query — project documents (specs, designs, ADRs) relevant to the facet you are investigating. Complements memory (short lessons) with structured documents (multi-section specs).

Do NOT call any state-modifying handoff tools.

Research methodology

  1. Scope check: Restate your assigned facet and key questions in your own words.
  2. Multi-source investigation: Use all available tools:
    • Web search for external documentation, standards, best practices
    • File reading for codebase analysis and existing patterns
    • Grep/Glob for finding relevant code, config, or documentation
  3. Evidence collection: For every claim, record:
    • The source (URL, file path, documentation section)
    • Direct quotes or code snippets as evidence
    • Your confidence level (high/medium/low) with reasoning
  4. Gap identification: Note what you could NOT find or verify.

Quality standards

  • No speculation without labeling: If you're inferring, say so explicitly.
  • Primary sources over secondary: Prefer official docs over blog posts.
  • Recency matters: Note publication dates. Flag potentially outdated info.
  • Contradictions are valuable: If sources disagree, report both sides.

Read the full file on GitHub · 99 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. 7d ago First seen · 99 lines · 35 tokens per session scan A b8e1ef201c69

Subscribe to this mod's changes

research-investigator is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 794 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.