dev-research

A research workflow that uses NotebookLM, a tool for asking questions about a selected collection of documents, to answer development questions with citations.

In plain words
What is it for?
Use it to research frameworks and tools such as Payload or Next.js, compare technology stacks, query project documentation, and search previous session notes.
Why use it?
It helps avoid relying on memory when checking specific documentation or decisions recorded in past development sessions.

Skill for Claude CodeCodex

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 skills/enakoneschniy/claude-dev-stack/dev-research
Any agent
npx skills add Enakoneschniy/claude-dev-stack --skill dev-research
Clone the repo
git clone --depth 1 https://github.com/Enakoneschniy/claude-dev-stack

Made for: Claude Code, Codex.

Per session 177 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,390 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 $0.00177 $0.01390
Opus 5 $0.00088 $0.00695
Sonnet 5 $0.00035 $0.00278
Haiku 4.5 $0.00018 $0.00139

Measured 2d ago against content hash 2f0253e243f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-research 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.

skills/dev-research/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Research Skill

Integrates NotebookLM into development workflow for grounded, citation-backed research. Uses notebooklm-py CLI for all NotebookLM interactions.

Prerequisites

# Check if notebooklm-py is installed
which notebooklm || echo "Install: pip install 'notebooklm-py[browser]'"

# Check auth
notebooklm auth check --test

Notebooks Convention

Each dev notebook follows naming: [Project] — [Purpose]

Examples:

  • "Crypto Portal — Stack Docs" (Payload CMS, Next.js docs)
  • "AI News Portal — CMS Research" (comparing CMS options)
  • "Dev Sessions Archive" (all session logs for cross-project search)

Commands

/research TOPIC

Research a topic using NotebookLM's grounded answers.

# Check if relevant notebook exists
notebooklm list 2>/dev/null | grep -i "TOPIC"

# If not, create one
notebooklm create "Research — TOPIC"
notebooklm use <notebook_id>

# Add sources — user provides URLs, or we search
notebooklm source add "URL1"
notebooklm source add "URL2"
notebooklm source add "./local-doc.md"

# Ask questions
notebooklm ask --json "QUESTION"

Parse JSON response and extract:

  • Answer text
  • Citations with source references
  • Confidence indicators

/docs-query QUESTION

Query project documentation notebook.

# Use the project's docs notebook
notebooklm use <project-docs-notebook-id>
notebooklm ask --json "QUESTION"

This gives grounded answers from actual documentation, not hallucinations.

/compare OPTION1 vs OPTION2

Create a structured comparison using NotebookLM.

notebooklm create "Comparison — OPTION1 vs OPTION2"
# Add documentation for both options
notebooklm source add "URL_OPTION1_DOCS"
notebooklm source add "URL_OPTION2_DOCS"

# Structured comparison questions
notebooklm ask --json "Compare OPTION1 and OPTION2 for: performance, DX, ecosystem, production readiness"
notebooklm ask --json "What are the main trade-offs between OPTION1 and OPTION2?"
notebooklm ask --json "Which is better for: [specific use case]?"

# Generate mind-map for visual comparison
notebooklm generate mind-map
notebooklm download mind-map ./vault/research/COMPARISON.json

Read the full file on GitHub · 195 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 · 195 lines · 177 tokens per session scan A 2f0253e243f3

Subscribe to this mod's changes

dev-research is a skill published in the GitHub repository Enakoneschniy/claude-dev-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 177 tokens to every session and 1,390 once invoked, about $0.0009 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 2026-08-31.

Related

Other skills, from other repositories

wiki-lint

Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…

AgriciDaniel/claude-obsidian · 79 tokens

mermaid-visualizer

Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.

breferrari/obsidian-mind · 57 tokens

release

Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.

lycorp-jp/sim-use · 61 tokens

session-retrospective

Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…

jpicklyk/task-orchestrator · 107 tokens

vc-web-testing

Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.

withkynam/vibecode-pro-max-kit · 51 tokens

bmad-dev-story

Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan".

LarsCowe/bmalph · 40 tokens