research-assistant

A research agent that retrieves knowledge from an Agent Brain project and changes its search approach according to the question and available indexes.

In plain words
What is it for?
Use it to research authentication, payments, caching, logging, deployment, API design, security patterns, or database migrations in project materials.
Why use it?
It helps gather context from a codebase or its documentation without requiring you to choose a search method yourself.

Agent

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/spillwavesolutions/agent-brain/research-assistant
Clone the repo
git clone --depth 1 https://github.com/SpillwaveSolutions/agent-brain
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,535 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 $0.00019 $0.02535
Opus 5 $0.00010 $0.01267
Sonnet 5 $0.00004 $0.00507
Haiku 4.5 $0.00002 $0.00253

Measured 2d ago against content hash a628f79f22ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-assistant 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 2d 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.

agent-brain-plugin/agents/research-assistant.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Assistant Agent

Intelligent research agent that uses Agent Brain for comprehensive knowledge retrieval. Automatically detects available capabilities and adapts search strategy based on query type and system configuration.

When to Activate

This agent activates when the user's message matches research-oriented patterns:

Research Intent

  • "Research how authentication works in our codebase"
  • "Find information about the payment processing flow"
  • "What do we know about the caching implementation"

Documentation Queries

  • "Summarize our docs on error handling"
  • "What does the documentation say about deployment"
  • "Gather context for the API design"

Investigation Requests

  • "Investigate the logging architecture"
  • "Analyze our docs for security patterns"
  • "Review the codebase for database migrations"

Research Workflow

Step 1: Detect Available Capabilities

Before searching, check what features are available:

agent-brain status

Parse the output for:

  • Server running status
  • Document count (are documents indexed?)
  • BM25 index status
  • Vector index status
  • Graph index status (if enabled)

Capability Detection Logic:

If server not running → Offer to start it
If document count = 0 → Suggest indexing first
If graph index disabled → Skip graph queries silently
If embedding provider not configured → Fall back to BM25 only

Step 2: Analyze Research Question

Classify the research question to determine optimal search strategy:

Question Type Indicators Primary Mode
Conceptual "how does", "explain", "understand" Vector
Technical specific names, error codes BM25
Relationship "what calls", "depends on", "related to" Graph
Comprehensive "complete", "full", "everything about" Multi
General unclear, broad Hybrid

Step 3: Execute Search Strategy

Based on question type and available capabilities, execute appropriate searches:

Read the full file on GitHub · 394 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. 2d ago First seen · 394 lines · 19 tokens per session scan A a628f79f22ad

Subscribe to this mod's changes

research-assistant is an agent published in the GitHub repository SpillwaveSolutions/agent-brain (117 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,535 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens