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 skills add nicojunk/claude-ig --skill ig-captiongit 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/skills/nicojunk/claude-ig/ig-caption)<a href="https://agentmods.dev/skills/nicojunk/claude-ig/ig-caption"><img src="https://agentmods.dev/badge/skills/nicojunk/claude-ig/ig-caption/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.
<a href="https://agentmods.dev/skills/nicojunk/claude-ig/ig-caption"><img src="https://agentmods.dev/badge/skills/nicojunk/claude-ig/ig-caption.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00100 | $0.01923 |
| Opus 5.5 | $0.00040 | $0.00769 |
| Sonnet 5.5 | $0.00020 | $0.00385 |
| Haiku 4.5 | $0.00010 | $0.00192 |
Grade A, and why
ig-caption 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 2mo 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IG Caption: Optimized Instagram Captions
Writes complete, paste-ready Instagram captions. Every caption follows a proven structure optimized for saves and DM-sends (the two highest-value algorithm signals in 2026). Captions sound like the creator wrote them. Never robotic, never filler.
Load account context (niche, audience, voice, language) from references/account-baseline.md.
If not configured, ask the user about their niche, audience, and voice.
Key references:
references/content-rules.md— Caption structure, CTA hierarchy, hashtag strategyreferences/scoring-system.md— Caption & CTA sub-criteria (20pts max)references/account-baseline.md— Proven caption patterns from top-performing posts
Workflow
Phase 1: Context
Gather the inputs needed to write a targeted caption.
- Identify post type — Reel, Carousel, Feed image, or Story highlight
- Identify topic — The specific content theme (e.g., "16:8 Fehler", "Proteinmythen", "Krafttraining ab 40")
- Identify visual hook — The text overlay or visual hook used on the post itself (needed to create a thematically linked but different caption opener)
- If any of these are missing, ask the user once. Do not proceed without all three.
Phase 2: Caption Structure
Load references/content-rules.md and apply the proven caption structure.
- Read content-rules.md for current caption structure rules, CTA hierarchy, and hashtag strategy
- Read account-baseline.md to identify which caption patterns performed best on recent top posts
- Map the structure for this specific post:
- Hook variation opener (thematically linked to visual hook, never identical)
- Value body (problem statement, insight, or actionable tip)
- Line break separator
- CTA (selected from hierarchy based on post type and goal)
- Hashtag set (3-5 niche-specific)
Phase 3: Writing
Write the complete caption in German following these rules.
3a. Hook Variation Opener
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.
- 2mo ago First seen · 199 lines · 100 tokens per session scan A 2b7e81eccff7
ig-caption is a skill published in the GitHub repository nicojunk/claude-ig (23 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,923 once invoked, about $0.0004 per session on Opus 5.5. 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.
ig-caption compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ig-captionnicojunk/claude-ig | Skill | 23 | 2mo ago | MIT | A | 100 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |