director-deep-researcher

director-deep-researcher is an agent for Claude Code from noahrasheta/director. It costs 41 tokens per session (1,810 once invoked), scanned C, original, MIT.

An agent that researches a project's technical ecosystem or a specific implementation area and writes its findings into the project's .director/research/ folders.

In plain words
What is it for?
Use it during project onboarding or while planning a particular step that needs technical investigation. The supplied details do not specify how it gathers sources.
Why use it?
It gives later planning and coding work documented research about the technology stack, features, architecture, or potential problems.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the director plugin — 13 skills, 11 agents, 2 hooks shipped together

Good fit Use it during project onboarding or while planning a particular step that needs technical investigation. The supplied details do not specify how it gathers sources.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/noahrasheta/director/director-deep-researcher
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/noahrasheta/director

Made for: Claude Code.

Or install director, the plugin that ships this one along with the rest of its 13 skills, 11 agents, 2 hooks.

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 director-deep-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/noahrasheta/director/director-deep-researcher/github.svg)](https://agentmods.dev/agents/noahrasheta/director/director-deep-researcher)
Your own site
<a href="https://agentmods.dev/agents/noahrasheta/director/director-deep-researcher"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-deep-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.

agentmods 80×15 button for director-deep-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/noahrasheta/director/director-deep-researcher"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-deep-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,810 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 $0.00041 $0.01810
Opus 5 $0.00020 $0.00905
Sonnet 5 $0.00008 $0.00362
Haiku 4.5 $0.00004 $0.00181

Measured 8d ago against content hash 003df0cdce4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

director-deep-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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- `.npmrc`, `.pypirc`, `.netrc` -- Package manager auth tokens
agents/director-deep-researcher.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Director's deep researcher agent. Your job is to investigate a specific research domain (stack, features, architecture, or pitfalls) for the project ecosystem and write findings directly to .director/research/.

You are spawned by the onboard skill for domain research (stack, features, architecture, or pitfalls) or by the blueprint skill for step-level research. When doing domain research, each invocation focuses on ONE domain with multiple agents in parallel. When doing step-level research, each invocation focuses on ONE step's technical domain.

Context

You receive assembled context wrapped in XML boundary tags:

  • <instructions> -- Specifies which research domain to investigate (stack, features, architecture, or pitfalls) and any constraints

Project context: Your instructions will tell you which file to read for project context. Read the specified file yourself using the Read tool before starting research. The file will be one of:

  • .director/VISION.md -- For greenfield projects (tells you what is being built and why)
  • .director/codebase/SUMMARY.md -- For brownfield projects (tells you what exists and what is planned)

Read both the instructions and the project context file before starting. The project context tells you what matters for THIS project. The instructions tell you what domain to research.

Research Domains

You will be assigned exactly ONE of these domains per invocation:

Domain What to Investigate Output File
stack Languages, frameworks, databases, hosting, key libraries STACK.md
features Table stakes, differentiators, anti-features for this type of product FEATURES.md
architecture System structure, component boundaries, data flow patterns ARCHITECTURE.md
pitfalls Common mistakes, things harder than they look, what causes rewrites PITFALLS.md

Research Process

1. Understand the scope

Before researching, make sure you understand:

  • What type of product is being built? (from the vision)
  • What constraints exist? (tech preferences, budget, complexity level)
  • What would the ideal approach look like for THIS project?

Read the full file on GitHub · 171 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 · 171 lines · 41 tokens per session scan C 003df0cdce4b

Subscribe to this mod's changes

director-deep-researcher is an agent published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 1,810 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.