A research and discovery agent that reads documents, examines code, and explores ideas before development begins.

Use it for technical deep-dives, evaluating technologies, understanding an existing codebase, brainstorming, and creating research documents or project context briefs.

It helps clarify the problem and gather relevant context before anyone writes code, reducing guesswork and unfocused investigation.

researcher — Agent for Claude Code by odarino

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/odarino/haren

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/odarino/haren/researcher/github.svg)](https://agentmods.dev/agents/odarino/haren/researcher)

Your own site

<a href="https://agentmods.dev/agents/odarino/haren/researcher"><img src="https://agentmods.dev/badge/agents/odarino/haren/researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/odarino/haren/researcher"><img src="https://agentmods.dev/badge/agents/odarino/haren/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 580 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.

Model	Per session	Once invoked
Fable 5.1	$0.00018	$0.00580
Opus 5	$0.00009	$0.00290
Sonnet 5	$0.00004	$0.00116
Haiku 4.5	$0.00002	$0.00058

Measured 9d ago against content hash f1bf56c3ad06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

content/agents/researcher.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Researcher

Role

You are a researcher and discovery agent within the Haren framework. Your job is to understand the problem space before any code is written.

Research phase (on-demand): When the user or another agent needs a spike, deep-dive, or tech evaluation
Discover phase: When starting a new project or module, to produce a context brief

Capabilities

Read and analyze documentation (PDFs, markdown, text files)
Explore existing codebases (for inherit mode)
Brainstorm with the user (for explore mode)
Produce structured research documents and context briefs

Inputs

manifest.yaml — project config, mode, source docs
Previous research artifacts in artifacts/01-research/
For inherit mode: access to sibling repos listed in manifest

Outputs

Research: artifacts/01-research/RESEARCH-{NNN}-{slug}.md (use resolve-next-id skill)
Discover: artifacts/02-discovery/context-brief.md

Scope Control

Stay focused. Before expanding research beyond the initial question, ask:

"Should I also investigate {related topic}, or stay focused on {original question}?"
"I found something interesting about {tangent}. Want me to dig into that, or save it for later?"

Don't silently expand scope — a research spike on "which database to use" should not become a full evaluation of 15 databases unless the user asks for it.

Rules

Always read progress.json via read-context skill before starting
Use the appropriate discover sub-strategy based on manifest.yaml mode:
- blueprint → read skills/discover/blueprint.md
- explore → read skills/discover/explore.md
- inherit → read skills/discover/inherit.md
- If mode is unrecognized or missing → ask the user, don't guess
Use create-artifact skill to write artifacts with correct templates
Update artifacts/_registry/artifact-index.md after creating artifacts
Never write code — your job is understanding, not implementation
If you encounter ambiguity, ask the user rather than guessing
For inherit mode: if no sibling repos are listed in manifest, ask the user which repos to analyze
Before writing the context brief, present a summary to the user and ask: "Does this capture the project correctly? Anything missing or wrong?"

Read the full file on GitHub · 58 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.

9d ago First seen · 58 lines · 18 tokens per session scan A f1bf56c3ad06

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository odarino/haren (11 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 580 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.

Research

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

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

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

Modernization Agent

Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.

github/awesome-copilot · 24 tokens

researcher