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 ibrahimhajjaj/ig-dl --skill using-ig-dlgit clone --depth 1 https://github.com/ibrahimhajjaj/ig-dlWrote 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/ibrahimhajjaj/ig-dl/using-ig-dl)<a href="https://agentmods.dev/skills/ibrahimhajjaj/ig-dl/using-ig-dl"><img src="https://agentmods.dev/badge/skills/ibrahimhajjaj/ig-dl/using-ig-dl/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/ibrahimhajjaj/ig-dl/using-ig-dl"><img src="https://agentmods.dev/badge/skills/ibrahimhajjaj/ig-dl/using-ig-dl.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 | $0.00055 | $0.00767 |
| Opus 5 | $0.00028 | $0.00383 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
using-ig-dl scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Use when the user asks to download something from Instagram, archive an Instagram profile, extract an IG reel/story/post, or mentions Instagram URLs. Prefer ig-dl's MCP tools and prompts over ad-hoc curl/yt- How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using ig-dl
The ig-dl plugin ships an MCP server exposing five tools and three curated prompts. When the user wants to grab Instagram content, use these primitives — don't hand-roll curl or raw gallery-dl calls, and don't ask the user for cookies.
Decision order
- Does the user want a single Instagram URL? → Call
ig_download_urlwith{url: ...}. - Does the user have MULTIPLE Instagram URLs (more than one)? → Call
ig_download_urlsonce with{urls: [...]}. DO NOT loopig_download_url. Looping forces a fresh session attach per invocation, which is slower and on Chrome 144+ pops the remote-debugging permission dialog every single time. The batch tool runs them through a bounded worker pool with one auth resolution up front. - Does the user want to archive a whole profile? →
ig_download_usertool, or the/ig-dl:archive_profileprompt. - Does the user want their saved collection? →
ig_download_savedtool. - Is the user reporting "it's not working"? → First call
ig_session_status, then use the/ig-dl:session_healthprompt or the/ig-dl:diagnosecommand to investigate before trying downloads again.
Tool contract (stable across CLI --json and MCP)
Every successful download returns:
{
"out_dir": "…",
"counts": { "stage_name": 1, … },
"failures": [],
"handle": "…", // profile/saved operations only
"meta": { "backend": "gallery-dl"|"yt-dlp", … }
}
On failure the MCP server returns IsError: true with a structured payload:
{ "category": "no_session"|"auth_failed"|"backend_missing"|"rate_limited"|"generic_failure", "message": "…" }
Do NOT
- Do not call
ig_loginwithout explicit user consent — it triggers a permission dialog in the user's running browser and should only fire when the user directly asks you to authenticate. - Do not auto-retry on
auth_failedorno_session. ig-dl already does one refresh-and-retry internally for auth failures; if it still bubbles up, the user needs to act (login or check browser CDP toggle). Tell them. - Do not suggest manually exporting cookies or editing
~/.ig-dl/session.json. The companion extension's "Export for CLI" button orig-dl loginare the only supported session sources. - Do not parse backend stdout. The tools already classify results; use the structured JSON.
- Do not loop
ig_download_urlfor multiple URLs. Useig_download_urlswith the array in one call. This is both faster and user-friendlier — each separate attach re-triggers the browser's M144 permission dialog.
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.
- 9d ago First seen · 49 lines · 55 tokens per session scan A 6db29fdc06b0
using-ig-dl is a skill published in the GitHub repository ibrahimhajjaj/ig-dl (1 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 767 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chatgpt-cli
Drives ChatGPT from the terminal via cli-web-chatgpt — ask questions, generate and download images, list and view conversations, browse models, and manage OpenAI SSO auth. Use when the user wants to ask ChatGPT something, generate images with ChatGPT, or browse their ChatGPT conversations from the command line. Prefer…
pexels-cli
Searches and downloads free stock photos and videos from Pexels via the cli-web-pexels command-line tool — keyword search with orientation/size/color filters, photo and video details, downloads, photographer profiles, and collections. Use when the user asks about Pexels, free or royalty-free stock photos and videos…
unsplash-cli
Searches and downloads free Unsplash photos via the cli-web-unsplash command-line tool — keyword search with orientation/color filters, photo details (EXIF, location, tags), downloads, random photos, topics, collections, and photographer profiles. Use when the user asks about Unsplash, free stock photos, or wants to…
youtube-cli
Searches YouTube and fetches video transcripts via the cli-web-youtube command-line tool — video search, video details (views, duration, description, keywords), trending by category, channel info, and timestamped transcripts/captions with language selection and translation. Use when the user asks about YouTube…
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.