deepwave

A deep web-research command with selectable depth and AI synthesis. It can combine multiple sources and research angles, then assess source quality and confidence.

In plain words
What is it for?
Use it for comprehensive research, complex topics, multiple viewpoints, and findings that need source evaluation or follow-up investigation.
Why use it?
It is designed for questions where a quick lookup is not enough and the evidence needs broader checking.

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/rowbradley/searchwave/deepwave
Any agent
npx skills add rowbradley/searchwave --skill deepwave
Clone the repo
git clone --depth 1 https://github.com/rowbradley/searchwave

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,087 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 $0.00034 $0.04087
Opus 5 $0.00017 $0.02044
Sonnet 5 $0.00007 $0.00817
Haiku 4.5 $0.00003 $0.00409

Measured 2d ago against content hash 4262b23f1240, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepwave 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/deepwave/SKILL.md · 551 lines

How it starts

The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Searchwave Deep

Deep web research with Opus synthesis — Quick (~70s) / Standard (~90s) / Max (~5-10min).

Overview

Three-tier research system with user-selected depth. All tiers use Opus (model default) for synthesis. Max mode adds multi-agent research with quality evaluation and follow-up loop.

Token-efficient alternative: Install searchwave-sonnet from the marketplace for Sonnet synthesis variants with the same research architecture.

When to Use

Use /deepwave when:

  • User wants to select research depth
  • Complex topics requiring multiple angles
  • Need confidence assessment and source evaluation
  • "Deep research" or "comprehensive" requests

Use /wave instead when:

  • Quick lookup, no questions needed
  • Simple factual questions
  • Time-sensitive (< 60 sec)

Use /searchwave-sonnet:deepwave instead when:

  • Token efficiency is a priority
  • Sonnet synthesis quality is sufficient

Phase 1: QA (~15 sec)

Use ONE AskUserQuestion call with 3-4 questions:

Question 1 (only if needed): Clarification Include if query has ambiguity OR broad scope needing focus.

Disambiguation (different meanings):

  • "Python" → programming language or snake?
  • "Mercury" → planet, element, or band?

Scope (same meaning, what to cover):

  • "home espresso" → machines? grinders? technique? beans? full setup?
  • "AI in gaming" → NPC behavior? dev tools? procedural generation?

Skip for focused queries:

  • "Python web frameworks" → clearly programming, clear scope
  • "Gaggia Classic Pro review" → specific enough

Question 2: Depth selection Always include:

"How deep should we go?"

- Quick (~1 min) — key facts, fast turnaround
- Standard (~2 min) — comprehensive research report
- Max (~5-10 min) — highest quality, multi-agent research, follow-up loop

Question 3: Length preference Always include. Show options based on tier:

"Preferred length?"

Quick tier options: 500 / 800 / 1200 words
Standard tier options: 800 / 1200 / 1500 words
Max tier options: 800 / 1200 / 1500+ words (1500+ means Opus may extend to ~2500 if valuable)

Read the full file on GitHub · 551 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 · 551 lines · 34 tokens per session scan A 4262b23f1240

Subscribe to this mod's changes

deepwave is a skill published in the GitHub repository rowbradley/searchwave (5 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 4,087 once invoked, about $0.0002 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.