research

research is a command for coding agents from sergei-aronsen/claude-code-toolkit. It costs 0 tokens per session (1,117 once invoked), scanned A, original, MIT.

A command for researching questions that need current information from several web sources, with citations. It can use a locally running browser signed in to Perplexity Pro.

In plain words
What is it for?
Use it to investigate recent software releases, library changes, security advisories, technology comparisons, market conditions, or regulatory updates.
Why use it?
It helps when built-in knowledge is not enough and you need recent, cross-checked facts rather than an answer based only on the current conversation.

Command

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 commands/sergei-aronsen/claude-code-toolkit/research
Clone the repo
git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit

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 research

README.md
[![agentmods](https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/research.svg)](https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/research)
Your own site
<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/research"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,117 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01117
Opus 5 $0.00000 $0.00558
Sonnet 5 $0.00000 $0.00223
Haiku 4.5 $0.00000 $0.00112

Measured 4d ago against content hash 00a6715db082, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research scanned grade A 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. CDP responds (`curl -s http://127.0.0.1:9223/json/version`).
commands/research.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/research — Deep Web Research via Perplexity Pro

Purpose

Run deep, multi-source research with citations through your Perplexity Pro subscription instead of paying per-token for the Sonar API. Routes through the optional comet-bridge MCP that talks to a locally-running Comet browser where you are logged into Perplexity.

Use for questions that need current web facts, not in-context reasoning: library deprecations, recent releases, security advisories, comparisons of competing tools, market state, regulatory changes.


Usage

/research <query>

Examples:

  • /research What changed in the Stripe API between Jan and May 2026?
  • /research Compare Bun, Deno, and Node.js for production HTTP services in 2026
  • /research Which Postgres connection poolers handle pgvector best?
  • /research Current state of WebAssembly Component Model adoption

When to Use

  • Question needs current facts (post-knowledge-cutoff data)
  • Multiple sources should be cross-referenced
  • Citations matter (auditing claims, drafting docs, evaluating tech)
  • You want a synthesized answer, not raw search results

Use /lookup instead when:

  • Single quick fact needed (~15s vs ~90s)
  • Don't need 15+ sources

Use /factcheck instead when:

  • You already have a claim and just want to verify it

Pre-flight Checks

Before running, this command verifies:

  1. comet-bridge MCP server is registered and ✓ connected in /mcp.
  2. Comet browser process is alive on CDP port 9223 (lsof -nP -iTCP:9223 -sTCP:LISTEN).
  3. CDP responds (curl -s http://127.0.0.1:9223/json/version).
  4. Perplexity is reachable (any tab on perplexity.ai exists, or comet_connect succeeds).

If any check fails, the command falls back to:

  • WebSearch (built-in Claude Code) for the query, and
  • context7 MCP for library docs (if installed),
  • prints a one-line hint: Run scripts/setup-comet.sh to enable Pro-subscription research without API costs.

Read the full file on GitHub · 141 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. 4d ago First seen · 141 lines · 0 tokens per session scan A 00a6715db082

Subscribe to this mod's changes

research is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,117 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.