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 skills/agentproto/ts/instagramnpx skills add agentproto/ts --skill instagramgit clone --depth 1 https://github.com/agentproto/tsWhat 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 | $0.00049 | $0.01357 |
| Opus 5 | $0.00024 | $0.00678 |
| Sonnet 5 | $0.00010 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
instagram 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 2d 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.
const r = await fetch(path, { How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instagram — recon plan (web private API)
✅ Instagram adapter —
SOCIAL_PLATFORMS.instagramin@agstudio/browser-social(sites/instagram/adapter.ts): profile · authored · connection (followers/following) · engagement-received (commenters — the only IG edge; likers 403), as aSocialSourcePort. In-pageigFetch(x-ig-app-id + x-csrftoken) + re-focus drift defense. Graph ingest:scripts/profile.ts instagram <username> --graph-only→ registry capture →landFootprintgraph sink (platform"instagram"): profile→SocialPerson, posts→AUTHORED, commenters→COMMENTED, followers/following→FOLLOWS. Same domain as LinkedIn → cross-platform queries just work. Likers stay 403.
✅ Validated live (logged in, read-only): headers
x-ig-app-id:936619743392459
x-csrftoken(csrftoken) +x-requested-with:XMLHttpRequest.web_profile_info?username=→200 (pk, full_name, follower/post counts).feed/user/<pk>/?count=N→200 (media: code, pk, like_count, comment_count, caption).media/<pk>/comments/→200 (commenters: @username + user pk + text = engagement edge). ⚠️media/<pk>/likers/→403 (IG hides likers). IG graph = followers/following + commenters, not likers. web_profile_info media edges are empty → usefeed/user/<pk>/.
Internal API: web private REST https://www.instagram.com/api/v1/... +
GraphQL https://www.instagram.com/graphql/query (and /api/graphql) using
doc_id. The web UI calls these directly.
Auth (from the page)
- cookies (
sessionid,csrftoken,ds_user_id) ride same-origin. - headers required:
x-ig-app-id: 936619743392459(the web app id — stable; also in the page's shared-data / a request header, capture to confirm),x-csrftoken: <csrftoken cookie>,x-requested-with: XMLHttpRequest,x-asbd-id(a small constant in requests — capture),x-ig-www-claim(echoed from a prior response headerx-ig-set-www-claim).
In-page fetch:
async path => {
const csrf = (document.cookie.match(/csrftoken=([^;]+)/) || [])[1]
const r = await fetch(path, {
headers: {
"x-ig-app-id": "936619743392459",
"x-csrftoken": csrf,
"x-requested-with": "XMLHttpRequest",
},
})
return await r.json()
}
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.
- 2d ago First seen · 109 lines · 49 tokens per session scan A f664a8ecbb17
instagram is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,357 once invoked, about $0.0002 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
excalidraw-diagrams
Use when asked to create or update Excalidraw diagrams. Provides guidance on Excalidraw best practices.
html-design-examples
Reference gallery of polished single-file HTML artifacts demonstrating effective ways to communicate ideas through HTML. Use when the user wants to explain, showcase, demo, plan, review, or present an idea within an HTML file.
transformers-js
Build and validate local browser or Bun inference with Hugging Face Transformers.js, WebGPU or WASM backends, quantization, caching, and cleanup.
browser-qa
Validate web applications through the embedded browser with responsive, interaction, console, and screenshot checks.
scene-designer
Activate this skill when users need help creating, modifying, or arranging visual elements in OBS scenes. Triggers include requests like "add a text overlay", "create a new scene", "move my webcam", "resize the game capture", "add a browser source", "arrange my layout", or designing scene compositions. This skill…
ai-agent-browser
业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。.