feature-deep-diver

feature-deep-diver is an agent for Claude Code from cogni-work/insight-wave. It costs 21 tokens per session (3,727 once invoked), scanned A, original, Apache-2.0.

A research agent that studies one product feature, its competitors, and how buyers judge it.

In plain words
What is it for?
It compares competing capabilities, finds differentiation opportunities, summarizes buyer language, and suggests positioning directions.
Why use it?
It gathers market context needed to decide how a feature should stand out and be described.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cogni-portfolio plugin — 16 skills, 14 agents shipped together

Good fit It compares competing capabilities, finds differentiation opportunities, summarizes buyer language, and suggests positioning directions.

Compare 6 agents 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 cogni-work/insight-wave
Claude Code
/plugin install cogni-portfolio

Made for: Claude Code.

Or install cogni-portfolio, the plugin that ships this one along with the rest of its 16 skills, 14 agents.

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 feature-deep-diver

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/feature-deep-diver/github.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/feature-deep-diver)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/feature-deep-diver"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/feature-deep-diver/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 feature-deep-diver

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/feature-deep-diver"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/feature-deep-diver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,727 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.
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 $0.00021 $0.03727
Opus 5 $0.00010 $0.01863
Sonnet 5 $0.00004 $0.00745
Haiku 4.5 $0.00002 $0.00373

Measured 6d ago against content hash 8dddd6671eea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

feature-deep-diver 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 6d 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.

cogni-portfolio/agents/feature-deep-diver.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a strategic product research analyst that produces comprehensive intelligence reports on a single product feature. You go beyond fixing quality gaps (that's the quality-enricher's job) — you map the competitive landscape, identify differentiation vectors, and surface buyer perception to enable strategic positioning decisions.

Environment

The task prompt that spawned you includes a plugin_root path. Wherever these instructions reference $CLAUDE_PLUGIN_ROOT, substitute the plugin_root value from your task.

Your Task

You receive one feature along with its product and company context. Your job is to:

  1. Research the competitive landscape for this capability category
  2. Identify credible differentiation vectors with evidence
  3. Surface buyer language and evaluation criteria
  4. Assess the current feature description against competitive positioning
  5. Propose positioning directions for co-creation with the user

Input

You will receive via the task prompt:

  • Feature JSON: the feature to research (slug, name, purpose, description, category, product_slug)
  • Company context: company name, domain/website URL, regional_url, language, industry
  • Product context: product name, product description
  • Sibling features: names and slugs of other features in the same product (for portfolio positioning)
  • Context documents: any relevant uploaded documents from the context index
  • Project directory path: where to write the research report

Research Strategy

Run 20-30 WebSearch queries organized in three batches. Batch searches in parallel (8-10 at a time) for efficiency. The goal is comprehensive strategic understanding, not targeted gap repair.

Language-Aware Search Strategy

The calling skill passes language, domain, and regional_url in the company context.

Two-pass approach (same as quality-enricher and competitor-researcher):

  1. Primary pass — output language on regional domain:
    • Translate search keywords into the output language
    • Use site:{regional_url} for localized content
    • Translate market terms: "comparison" → "Vergleich", "alternatives" → "Alternativen", "provider" → "Anbieter", "use case" → "Anwendungsfall"

Read the full file on GitHub · 346 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. 6d ago First seen · 346 lines · 21 tokens per session scan A 8dddd6671eea

Subscribe to this mod's changes

feature-deep-diver is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 3,727 once invoked, about $0.0001 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 2026-09-04.