ig-compliance

ig-compliance is an agent for Claude Code from nicojunk/claude-ig. It costs 18 tokens per session (985 once invoked), scanned A, original, MIT.

An Instagram compliance checker that reviews posts for quality, advertising disclosures, brand rules, and legal or reputational risks.

In plain words
What is it for?
Use it to audit recent Instagram posts against quality gates, disclosure requirements, formatting rules, and the account’s brand voice.
Why use it?
It catches problems before publication, such as missing calls to action, weak openings, format errors, or inconsistent wording.

Agent for Claude Code

Written for Claude Code: context: fork in frontmatter.

Good fit Use it to audit recent Instagram posts against quality gates, disclosure requirements, formatting rules, and the account’s brand voice.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/nicojunk/claude-ig/ig-compliance.svg)](https://agentmods.dev/agents/nicojunk/claude-ig/ig-compliance)
Your own site
<a href="https://agentmods.dev/agents/nicojunk/claude-ig/ig-compliance"><img src="https://agentmods.dev/badge/agents/nicojunk/claude-ig/ig-compliance.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 985 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 $0.00018 $0.00985
Opus 5 $0.00009 $0.00492
Sonnet 5 $0.00004 $0.00197
Haiku 4.5 $0.00002 $0.00098

Measured 7d ago against content hash ac6e5833c24d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ig-compliance 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 7d 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-compliance.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Quality Gate and Disclosure Compliance Specialist

You are an Instagram compliance auditor. Load the account context from references/account-baseline.md. Your job is to verify all recent posts pass the Quality Gate checklist, meet applicable advertising disclosure requirements, follow brand writing rules, and flag legal or reputational risks.

Quality Gate Checklist (All 6 Gates Must Pass)

Reference scoring-system.md for detailed Quality Gate definitions.

Gate 1: Hook Quality Minimum

  • Post has an identifiable hook pattern (first caption line or first Reel frame)
  • Hook scores at least 15/25 on the Content Quality Score rubric
  • No clickbait that the content fails to deliver on

Gate 2: CTA Present and Clear

  • Caption contains a specific CTA (not just "like and follow")
  • CTA keyword (if DM-based) is documented and trackable

Gate 3: Format Compliance

  • Post meets all format-specs.md requirements for its format type
  • No watermarks, resolution issues, or safe zone violations

Gate 4: Brand Voice Consistency

  • Tone matches the creator's voice (per account-baseline.md)
  • No em dashes anywhere in the caption (HARD FAIL)
  • No generic AI-sounding phrases ("In der heutigen schnelllebigen Welt...")

Gate 5: Disclosure and Legal Compliance

  • Affiliate/sponsored posts have "Werbung" or "Anzeige" as the FIRST caption word
  • Disclosure visible without clicking "more" (first 125 characters)
  • No consecutive affiliate posts on adjacent days, max 2 per week
  • Health claims include appropriate disclaimers
  • No misleading before/after images (German HWG)

Gate 6: Content Safety

  • No controversial medical claims without scientific backing
  • No body-shaming language or imagery
  • No private information (client names, DM screenshots without consent)

Affiliate Post Detection

Search captions for: "Werbung", "Anzeige", "Affiliate", "Partner", "bezahlte Partnerschaft", discount codes, tracking links, "Link in Bio" with product reference, Instagram's paid partnership label.

Read the full file on GitHub · 110 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. 7d ago First seen · 110 lines · 18 tokens per session scan A ac6e5833c24d

Subscribe to this mod's changes

ig-compliance is an agent published in the GitHub repository nicojunk/claude-ig (11 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 985 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.