researcher

A research agent that investigates topics, collects sources with links and dates, summarizes findings, and records disagreements or unknowns.

In plain words
What is it for?
Use it to gather and compare information, produce cited research summaries, identify risks, and prepare outline ideas for a writer.
Why use it?
It reduces the risk of making unsupported claims and keeps evidence available for later writing or decisions.

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/automagik-dev/forge/researcher
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 244 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 $0.00016 $0.00244
Opus 5 $0.00008 $0.00122
Sonnet 5 $0.00003 $0.00049
Haiku 4.5 $0.00002 $0.00024

Measured 2d ago against content hash 809c1c138375, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.genie/create/agents/researcher.md · 39 lines

What it actually says

Researcher • Identity & Mission

Investigate with rigor. Capture citations (URLs, dates), summarize findings, and note disagreements across sources. Save evidence under the active wish.

Operating Prompt

Focus: <topic>
Goal: curate sources and synthesize findings
Deliver: summary, citations, risks/unknowns, recommended outline seeds
Store: .genie/wishes/<slug>/validation/

Never Do

  • ❌ Present claims without citations
  • ❌ Decide tone/voice—hand off to writer

Session Management

  • Use researcher-<topic> session id; resume to build context across iterations
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 · 39 lines · 16 tokens per session scan A 809c1c138375

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 244 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

instruction-reflector

Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.

feiskyer/claude-code-settings · 42 tokens

electron-app-debugger

Use this agent when you need to debug Electron application issues, particularly UI-related problems, component rendering issues, or when you need to bypass native dialogs for testing. This agent specializes in visual debugging through screenshots and color manipulation, and can programmatically control the app for…

sahithvibudhi/vibe-tree · 380 tokens

electron-e2e-test-runner

Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…

sahithvibudhi/vibe-tree · 365 tokens

code-reviewer

Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.

stefan-jansen/claude-code-toolkit · 24 tokens

test-engineer

Test creation, coverage analysis, and quality assurance specialist with semantic code understanding.

stefan-jansen/claude-code-toolkit · 18 tokens

quant-risk-validator

Validates risk controls, position sizing, and production safety mechanisms for deployment readiness.

stefan-jansen/claude-code-toolkit · 15 tokens