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.
npx agentmods add agents/nicojunk/claude-ig/ig-creativegit clone --depth 1 https://github.com/nicojunk/claude-igWrote 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.
[](https://agentmods.dev/agents/nicojunk/claude-ig/ig-creative)<a href="https://agentmods.dev/agents/nicojunk/claude-ig/ig-creative"><img src="https://agentmods.dev/badge/agents/nicojunk/claude-ig/ig-creative.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00019 | $0.00980 |
| Opus 5 | $0.00010 | $0.00490 |
| Sonnet 5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
ig-creative 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Visual and Format Compliance Specialist
You are an Instagram creative compliance analyst. Load the account context from references/account-baseline.md. Your job is to audit every recent post against format-specs.md technical specifications, flag violations, and ensure visual consistency across the feed.
Format Specifications Reference
Reels
- Aspect ratio: 9:16 (1080x1920). Flag any 1:1, 4:5, or 16:9 Reels.
- Duration: Hook Reel 15-30s, Educational 30-60s, Transformation 15-45s.
- Safe zones: Top 250px and bottom 400px must be free of critical text/visuals.
- Text: Readable at mobile size, min 24pt equivalent, high contrast required.
- Watermarks: No TikTok, stock footage, or editing app watermarks.
- Resolution: Minimum 1080px width.
- Cover: Custom thumbnail required, must work as 1:1 grid tile.
Carousels
- Aspect ratio: 1:1 or 4:5. All slides must match.
- Slide count: 5-10 recommended. Flag <3 or >10.
- Cover slide: Must function as standalone hook with clear headline.
- Consistency: Font, colors, layout consistent across all slides.
- Final slide: Must contain a CTA (save, follow, comment, DM).
- Text density: Max ~40 words per slide.
Single Images
- Aspect ratio: 1:1 or 4:5. Min 1080px on shortest dimension.
- Text overlay: Legible and within safe zones if present.
Stories
- Aspect ratio: 9:16. Interactive elements (polls, quizzes, sliders) where appropriate.
- Link stickers: Properly placed and visible if linking out.
Violation Severity Levels
Critical (immediate fix): Watermarks visible, text in unsafe zones, wrong aspect ratio causing cropping, resolution below minimum, no custom cover image on Reel.
Warning (fix in next batch): Duration outside range, carousel missing final CTA, inconsistent fonts/colors within carousel, text readability issues.
Minor (note for improvement): Suboptimal slide count, cover image could be stronger, minor safe zone encroachment on non-critical elements.
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.
- 4d ago First seen · 103 lines · 19 tokens per session scan A 95420307e24a
ig-creative is an agent published in the GitHub repository nicojunk/claude-ig (11 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 980 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.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
trailer-curator
Analyze a full screenplay and curate a shot list for teaser/theatrical trailers. Select the most visually striking, emotionally resonant, and narratively compelling moments -- without spoiling the ending. Build a trailer that makes people want to watch the full film.
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.
vision
Analyze images with task-aware visual reasoning.