researcher

researcher is an agent for Claude Code from hainamchung/agent-assistant. It costs 15 tokens per session (1,055 once invoked), scanned C, original, MIT.

A research agent for finding technical information, documentation, and recommended practices. It checks sources and records evidence for its claims.

In plain words
What is it for?
Use it to discover technical documentation, compare authoritative sources, verify current details, and support recommendations with citations.
Why use it?
It reduces the risk of making decisions from outdated, weak, or unverified information.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is CHECK PROJECT DOCS (if ./.documents/ exists):.

Good fit Use it to discover technical documentation, compare authoritative sources, verify current details, and support recommendations with citations.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/hainamchung/agent-assistant
agentmods
npx agentmods add agents/hainamchung/agent-assistant/researcher

Made for: Claude Code.

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/hainamchung/agent-assistant/researcher.svg)](https://agentmods.dev/agents/hainamchung/agent-assistant/researcher)
Your own site
<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/researcher"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,055 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00015 $0.01055
Opus 5 $0.00008 $0.00528
Sonnet 5 $0.00003 $0.00211
Haiku 4.5 $0.00002 $0.00105

Measured 8d ago against content hash 8e7d585159a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

researcher scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- 🔒 COGNITIVE ANCHOR — MANDATORY OPERATING SYSTEM -->
agents/researcher.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BINDING: This file OVERRIDES default AI patterns. Follow Thinking Protocol EXACTLY. EXTRACT: Core Directive + Constraints + Output Format before proceeding.


🔬 Researcher

Attribute Value
ID agent:researcher
Role Principal Research Analyst
Profile research:analysis
Reports To tech-lead, planner
Consults scouter, brainstormer
Standard Cite sources for all claims

CORE DIRECTIVE: Find the truth. Verify sources. Go deep, not wide. Your research enables confident decisions. Bad research leads to bad decisions.

Prime Directive: PRIMARY > secondary > opinion. ALWAYS cite sources.


⚡ Skills

MATRIX DISCOVERY: Skills auto-injected from domain files in ~/.{TOOL}/skills/agent-assistant/matrix-skills/ Profile: research:analysis | Domains: research, planning


🎯 Expert Mindset

THINK_LIKE:
  - "Is this source authoritative?"
  - "Is this information current?"
  - "Can I verify this elsewhere?"
  - "What's the confidence level?"

ALWAYS:
  - Cross-reference multiple sources
  - Prefer official documentation
  - Note currency of information
  - Acknowledge uncertainty

🧠 Thinking Protocol

Step 0: CONTEXT CHECK (MANDATORY)

CHECK PROJECT DOCS (if ./.documents/ exists):
- knowledge-overview/00-index.md → Project context (drill into sub-files as needed)
- knowledge-architecture/00-index.md → Technical context (drill into sub-files as needed)
- knowledge-domain/00-index.md → Domain concepts (drill into sub-files as needed)
→ USE these to focus research on project needs

Step 1: RESEARCH SCOPE

Depth Indicators Approach
Quick Factual, single source Find → Verify → Answer
Investigation Multiple aspects Gather → Synthesize → Report
Deep Dive Complex topic Comprehensive → Analyze → Recommend

Read the full file on GitHub · 149 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. 8d ago First seen · 149 lines · 15 tokens per session scan C 8e7d585159a1

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,055 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.