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-storygit 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-story)<a href="https://agentmods.dev/skills/nicojunk/claude-ig/ig-story"><img src="https://agentmods.dev/badge/skills/nicojunk/claude-ig/ig-story/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-story"><img src="https://agentmods.dev/badge/skills/nicojunk/claude-ig/ig-story.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 | $0.00038 | $0.00984 |
| Opus 5.5 | $0.00015 | $0.00394 |
| Sonnet 5.5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
ig-story 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IG Story -- Plan engaging Instagram Story sequences
Key references:
references/format-specs.md-- dimensions, duration limits, safe zonesreferences/content-rules.md-- brand voice, banned topics, caption rulesreferences/story-strategy.md-- story arc patterns, frequency targets, sticker usage
Phase 1: Context
- Ask the user for the story goal (one of: educate, engage, sell, entertain, build trust).
- Confirm the topic or product to feature.
- If a specific date or campaign is mentioned, note any calendar constraints.
- Load all key reference files listed above before proceeding.
Phase 2: Story Type Selection
Select one primary story type based on the goal:
| Goal | Story Type | Characteristics |
|---|---|---|
| Educate | Educational | Tip sequence, "Wusstest du...?" opener, text-heavy slides |
| Engage | Poll / Quiz | Interactive stickers, opinion-based, low friction |
| Sell | Product Spotlight | Demo or testimonial, swipe-up / link sticker, clear CTA |
| Entertain | Behind-the-Scenes | Raw footage feel, casual voice, day-in-the-life |
| Build Trust | Social Proof | Screenshots, results, user messages (anonymized) |
Document the selected type and reasoning.
Phase 3: Slide Sequence
Build the sequence with a maximum of 5 slides. Each slide must specify:
- Slide number (1-5)
- Visual description -- what the viewer sees (photo, video clip, graphic)
- Text overlay -- large text, high contrast, max 2 lines per slide
- Duration -- 5s for static, up to 15s for video
- Transition note -- how it connects to the next slide
Slide Sequence Rules
- Slide 1 is the hook. It must stop the tap-through. Use a bold statement or question.
- Middle slides deliver the payload (info, proof, entertainment).
- Final slide contains the CTA or interactive element.
- Text overlays: minimum 24pt equivalent, always within safe zone (see format-specs.md).
- High contrast required: white text on dark overlay, or dark text on light overlay.
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 · 125 lines · 38 tokens per session scan A 19f146e52fbb
ig-story is a skill published in the GitHub repository nicojunk/claude-ig (23 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 984 once invoked, about $0.0002 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-story compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ig-storynicojunk/claude-ig | Skill | 23 | 2mo ago | MIT | A | 38 | 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 |