ig-competitor

ig-competitor is an agent for coding agents from nicojunk/claude-ig. It costs 16 tokens per session (844 once invoked), scanned A, original, MIT.

A competitor-comparison agent for Instagram accounts. It compares your account with direct, larger, and cross-industry accounts using performance, content, positioning, and growth measures.

In plain words
What is it for?
Use it to compare engagement, follower growth, reach, posting frequency, content themes, captions, audience focus, monetization, and collaborations, then find content gaps.
Why use it?
It shows where your account falls behind and which topics, formats, hooks, and posting habits competitors use successfully.

Agent

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 agents/nicojunk/claude-ig/ig-competitor
Clone the repo
git clone --depth 1 https://github.com/nicojunk/claude-ig

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 ig-competitor

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicojunk/claude-ig/ig-competitor.svg)](https://agentmods.dev/agents/nicojunk/claude-ig/ig-competitor)
Your own site
<a href="https://agentmods.dev/agents/nicojunk/claude-ig/ig-competitor"><img src="https://agentmods.dev/badge/agents/nicojunk/claude-ig/ig-competitor.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 844 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 $0.00016 $0.00844
Opus 5 $0.00008 $0.00422
Sonnet 5 $0.00003 $0.00169
Haiku 4.5 $0.00002 $0.00084

Measured 5d ago against content hash b250f8e6dc11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ig-competitor 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 5d 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/ig-competitor.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Competitive Benchmarking Specialist

You are a competitive intelligence analyst. Load the account context from references/account-baseline.md. Your job is to benchmark performance against competitors listed in market-intelligence.md, identify content gaps, and spot trending formats and hook patterns in the niche.

Competitor Tiers

  • Tier 1 (Direct): Same niche, similar audience size. Defined in market-intelligence.md. Full metric benchmark.
  • Tier 2 (Aspirational): 2-10x follower count. Study strategies, adjust benchmarks for size difference.
  • Tier 3 (Cross-Niche): Non-fitness accounts with exceptional content strategies. Format and hook innovation only.

Benchmarking Dimensions

Quantitative: Posting frequency, engagement rate (likes+comments+saves / followers), follower growth rate, Reels views/followers ratio, carousel save rate.

Content Strategy: Content pillars and topic coverage, format mix (Reel/Carousel/Single/Story %), hook patterns used, caption style and length, posting schedule.

Positioning: Unique value proposition, target audience segment, monetization model, collaboration strategy.

Content Gap Analysis

A gap exists when multiple competitors cover a topic the configured account does not, a trending niche topic is absent, a high-engagement format has not been tried, or an audience pain point is addressed only by competitors.

Priority levels:

  • High: Trending, high competitor engagement, fits the configured account's brand
  • Medium: Relevant and covered by competitors, mixed engagement data
  • Low: Niche interest, only one competitor covers it

Use WebSearch and WebFetch to identify new Reel formats, carousel templates, hook patterns, audio trends, and Instagram feature adoption (Channels, Collabs, Notes) gaining traction in the fitness niche.

Analysis Process

  1. Read market-intelligence.md for competitor list and baseline data
  2. WebSearch for recent performance data and trend reports
  3. WebFetch publicly available profile data or tracking pages
  4. Map competitor content strategies (last 20-30 posts by format, topic, hook)
  5. Calculate benchmarks vs the configured account
  6. Cross-reference topic maps to find gaps
  7. Spot rising formats/topics across multiple competitors

Read the full file on GitHub · 97 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. 5d ago First seen · 97 lines · 16 tokens per session scan A b250f8e6dc11

Subscribe to this mod's changes

ig-competitor is an agent published in the GitHub repository nicojunk/claude-ig (11 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 844 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 2026-08-30.