deep-research

deep-research is a skill for Claude Code from billy-enrizky/openbrowser-ai. It costs 82 tokens per session (7,588 once invoked), scanned A, original, MIT.

A research workflow that investigates a question across multiple web sources and produces a cited Markdown report and structured JSON files.

In plain words
What is it for?
Use it for topic research, deep dives, evidence gathering, and comparisons that need source citations.
Why use it?
It breaks a broad question into smaller investigations and combines the findings, so you do not have to search, compare, and organize sources by hand.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/foo/myproject.

Part of the openbrowser plugin — 7 skills shipped together

Good fit Use it for topic research, deep dives, evidence gathering, and comparisons that need source citations.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add billy-enrizky/openbrowser-ai
Claude Code
/plugin install openbrowser

Made for: Claude Code.

Or install openbrowser, the plugin that ships this one along with the rest of its 7 skills.

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 deep-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/billy-enrizky/openbrowser-ai/deep-research.svg)](https://agentmods.dev/skills/billy-enrizky/openbrowser-ai/deep-research)
Your own site
<a href="https://agentmods.dev/skills/billy-enrizky/openbrowser-ai/deep-research"><img src="https://agentmods.dev/badge/skills/billy-enrizky/openbrowser-ai/deep-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,588 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. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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 $0.00082 $0.07588
Opus 5 $0.00041 $0.03794
Sonnet 5 $0.00016 $0.01518
Haiku 4.5 $0.00008 $0.00759

Measured 8d ago against content hash 14c5c643dc96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deep-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 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.

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.

plugin/skills/deep-research/SKILL.md · 688 lines

How it starts

The opening of the file, as written. The whole thing — 688 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Research

Drive openbrowser-ai to investigate a topic across multiple web sources and produce a cited markdown report plus structured JSON. Two modes:

  • flat synthesis (default) -- decompose query into 3-7 sub-questions, dispatch one parallel sub-agent per sub-question (each owns one tab), merge into one cited report.
  • drilldown (auto-detected from prompt phrasing: "deep dive", "exhaustive", "recursive", "drilldown", "thorough") -- same as flat, plus a second wave of parallel sub-agents on findings flagged needs_depth=true. Hard cap depth=2, max 3 follow-up sub-agents per parent.

Output paths (relative to current project root):

  • local_docs/research/YYYY-MM-DD-<slug>.md
  • local_docs/research/YYYY-MM-DD-<slug>.json

Architecture (mandatory): the orchestrating Claude session (the one running this skill) MUST dispatch parallel sub-agents via /dispatching-parallel-agents, one sub-agent per sub-question. Each sub-agent owns exactly ONE tab. Sub-agents do not open additional tabs. The orchestrator merges per-agent findings into one report.

Why one tab per sub-agent and not asyncio.gather over tabs in a single -c call: a single Python coroutine driving N tabs through one daemon serializes navigation events at the CDP layer, contends for the LLM-extraction worker, and cannot make independent decisions about pagination or follow-up clicks per tab. Dispatching real Claude sub-agents (each with its own context window and its own browser tab) gives true parallelism, independent reasoning per tab, and isolates failures so one bad page doesn't poison the rest.

Hard rules:

  • One sub-agent = one tab. Sub-agents must NOT call navigate(url, new_tab=True) to spawn additional tabs.
  • All sub-agents share the same daemon (and so the same Chrome process). Tabs are isolated; navigation in one tab does not affect another.
  • Each sub-agent writes its findings to its own JSON file under local_docs/research/_partial/<slug>-NN.json. The orchestrator reads and merges these.
  • The orchestrator never drives tabs itself. It only plans, dispatches, merges, renders, verifies, cleans up.

If a first-wave sub-agent returns <2 findings, the orchestrator dispatches a Step 2b retry sub-agent with broader search strategy (alternative engines, query reformulation, lower thresholds). Still -c-only: the skill never calls openbrowser-ai -p.

Variables persist across -c calls in the daemon namespace.

Session reuse: Step 0 checks openbrowser-ai daemon status. If a daemon is already running (warm browser), the skill reuses it and operates in NEW tabs (never disturbs the user's existing tabs). If no daemon, the skill auto-starts one on first -c call.

Every factual claim in the report carries a footnote citation [N]. Verifier fails the run if uncited prose is found.

Read the full file on GitHub · 688 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 · 688 lines · 82 tokens per session scan E 14c5c643dc96

Subscribe to this mod's changes

deep-research is a skill published in the GitHub repository billy-enrizky/openbrowser-ai (241 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 7,588 once invoked, about $0.0004 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 skills, from other repositories

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

cloud-sync

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.

thedotmack/claude-mem · 64 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

ci-security-scanning-with-strix

Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…

usestrix/strix · 140 tokens

extract

Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.

semantica-agi/semantica · 59 tokens

pinchtab-stealth-score

Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…

pinchtab/pinchtab · 168 tokens