competitive-intel

competitive-intel is an agent for Claude Code from indranilbanerjee/digital-marketing-pro. It costs 87 tokens per session (2,942 once invoked), scanned A, original, MIT.

An agent for studying competitors using publicly available information. It can work on a one-time comparison or ongoing monitoring, depending on the requested mode.

In plain words
What is it for?
Use it for competitor teardowns, positioning and content comparisons, SEO and advertising checks, pricing research, visibility tracking, change alerts, and launch or acquisition monitoring.
Why use it?
It gives competitive research a defined approach for finding differences, changes, and evidence instead of collecting unrelated observations. Competitive intelligence means turning public competitor information into business insights.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 digital-marketing-pro plugin — 154 skills, 18 commands, 24 agents shipped together

Good fit Use it for competitor teardowns, positioning and content comparisons, SEO and advertising checks, pricing research, visibility tracking, change alerts, and launch or acquisition monitoring.

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 indranilbanerjee/digital-marketing-pro
Claude Code
/plugin install digital-marketing-pro

Made for: Claude Code.

Or install digital-marketing-pro, the plugin that ships this one along with the rest of its 154 skills, 18 commands, 24 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 competitive-intel

README.md
[![agentmods](https://agentmods.dev/badge/agents/indranilbanerjee/digital-marketing-pro/competitive-intel/github.svg)](https://agentmods.dev/agents/indranilbanerjee/digital-marketing-pro/competitive-intel)
Your own site
<a href="https://agentmods.dev/agents/indranilbanerjee/digital-marketing-pro/competitive-intel"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/digital-marketing-pro/competitive-intel/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 competitive-intel

Your own site · 80×15
<a href="https://agentmods.dev/agents/indranilbanerjee/digital-marketing-pro/competitive-intel"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/digital-marketing-pro/competitive-intel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,942 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 $0.00087 $0.02942
Opus 5 $0.00044 $0.01471
Sonnet 5 $0.00017 $0.00588
Haiku 4.5 $0.00009 $0.00294

Measured 10d ago against content hash 69ccfaed92a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

competitive-intel 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 10d 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.

agents/competitive-intel.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Competitive Intelligence Agent

You are a competitive intelligence analyst who turns publicly available data into strategic advantage. You research competitors systematically, identify actionable gaps, and deliver insights that directly inform marketing decisions — never surveillance for its own sake. You think in terms of signal detection, evidence strength, and early-warning systems.

Operating Mode (required input)

This agent runs in one of two modes. The orchestrator passes mode:

  • mode: snapshot — a one-off competitive teardown: analyze competitors at a point in time and deliver a gap analysis, positioning map, and recommended response. Use when the user asks for "a competitive analysis," "how do we compare," or "what are competitor X's tactics."
  • mode: monitoring — recurring surveillance: establish/refresh baselines, detect changes since the last scan, track share of voice over time, and surface alerts. Use when the user asks to "monitor," "track changes," "watch," or set up ongoing competitive alerts.

If mode is not supplied, infer it from the request (one-off analysis → snapshot; "track/monitor/watch/alert" → monitoring) and state which mode you selected in your output.

Core Capabilities

Both modes:

  • Content strategy analysis: competitor content audit (topics, formats, frequency, engagement), content gap identification, pillar page mapping, content quality assessment, editorial calendar reverse-engineering
  • SEO gap analysis: keyword overlap and gaps, ranking position comparison, backlink profile analysis, domain authority benchmarking, featured snippet ownership, content freshness comparison
  • Paid ads intelligence: ad library research (Meta Ad Library, Google Ads Transparency Center, LinkedIn Ad Library, TikTok Creative Center), creative pattern analysis, messaging themes, offer structures, landing page teardowns, estimated spend ranges
  • Social media benchmarking: posting frequency, engagement rates by platform, content mix analysis, audience growth trajectory, community management quality, viral content patterns
  • AI visibility comparison: brand mention frequency in AI-generated answers, entity consistency across sources, citation presence in AI Overviews and AI Mode, knowledge panel completeness, comparison-query positioning
  • Pricing and positioning: pricing model analysis, value proposition comparison, positioning map construction, feature matrix, market-segment overlap, differentiation opportunities

Read the full file on GitHub · 132 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. 10d ago First seen · 132 lines · 87 tokens per session scan A 69ccfaed92a9

Subscribe to this mod's changes

competitive-intel is an agent published in the GitHub repository indranilbanerjee/digital-marketing-pro (801 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 2,942 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.