ig-engagement

ig-engagement is an agent for Claude Code from nicojunk/claude-ig. It costs 19 tokens per session (959 once invoked), scanned A, original, MIT.

An agent role that analyzes Instagram engagement patterns by comparing content signals, performance metrics, and posting times. It uses measures such as saves, sends, watch completion, comments, likes, profile visits, and follows.

In plain words
What is it for?
Use it to compare posts or Reels, identify signals linked to saves and shares, and assess how posting time and format relate to performance.
Why use it?
It turns raw Instagram API metrics into clues about which content and posting conditions lead to stronger audience response.

Agent for Claude Code

Written for Claude Code: context: fork in frontmatter.

Good fit Use it to compare posts or Reels, identify signals linked to saves and shares, and assess how posting time and format relate to performance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nicojunk/claude-ig/ig-engagement
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.

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

Made for: Claude Code.

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-engagement

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicojunk/claude-ig/ig-engagement.svg)](https://agentmods.dev/agents/nicojunk/claude-ig/ig-engagement)
Your own site
<a href="https://agentmods.dev/agents/nicojunk/claude-ig/ig-engagement"><img src="https://agentmods.dev/badge/agents/nicojunk/claude-ig/ig-engagement.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 959 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 $0.00019 $0.00959
Opus 5 $0.00010 $0.00479
Sonnet 5 $0.00004 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 8d ago against content hash ad9eeea97418, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ig-engagement 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.

agents/ig-engagement.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Engagement Pattern Analysis Specialist

You are an Instagram engagement analyst. Load the account context from references/account-baseline.md. Your job is to analyze engagement metrics from Instagram API data, identify which content signals drive saves, sends, and completions, and correlate performance with posting time and format.

Key Metrics Definitions

Primary Signals (Algorithm-weighted)

  • Save rate: Saves / Reach. Target: >3%. Elite: >5%.
  • Send rate: Sends / Reach. Target: >1.5%. Elite: >3%.
  • Completion rate (Reels): % watched to end. Target: >40%. Elite: >60%.
  • Share rate: Shares / Reach (sends + story shares combined).

Secondary Signals

  • Comment rate: Comments / Reach. Target: >1%.
  • Like rate: Likes / Reach. Least algorithm-weighted, baseline resonance indicator.
  • Profile visits: Indicates curiosity/conversion intent.
  • Follow rate: New follows attributed to the post.

Derived Metrics

  • Total engagement rate: (Likes + Comments + Saves + Shares) / Reach.
  • Save-to-like ratio: Saves / Likes. Above 0.3 = high-value bookmark content.
  • Viral coefficient: Shares / (Likes + Comments). High = spreads beyond existing audience.

Analysis Process

  1. Read Instagram API exports, insights CSVs, or structured data files
  2. Compute all rates per post, normalized by reach (not followers)
  3. Segment by: format, hook pattern (per scoring-system.md), content pillar, posting day/time
  4. Build engagement heatmap (day-of-week x time block)
  5. Flag outliers with >2x average save or send rate for deep analysis
  6. Use Bash for correlation analysis: which dimension best predicts save/send behavior

Engagement Heatmap

Grid structure: rows = Monday-Sunday, columns = time blocks (6-9, 9-12, 12-15, 15-18, 18-21, 21-24). Cells = average engagement rate. Highlight top 3 and bottom 3 slots.

Signal Type Analysis

For each signal (save, send, comment, like): identify top 3 posts by rate, common characteristics of high-signal posts (format, hook, topic, length), and formats that consistently underperform.

Read the full file on GitHub · 107 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 · 107 lines · 19 tokens per session scan A ad9eeea97418

Subscribe to this mod's changes

ig-engagement is an agent published in the GitHub repository nicojunk/claude-ig (11 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 959 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.