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 commands/shivang0/social-vision/analyzegit clone --depth 1 https://github.com/Shivang0/social-visionWrote 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/commands/shivang0/social-vision/analyze)<a href="https://agentmods.dev/commands/shivang0/social-vision/analyze"><img src="https://agentmods.dev/badge/commands/shivang0/social-vision/analyze.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 | $0.00030 | $0.00243 |
| Opus 5 | $0.00015 | $0.00121 |
| Sonnet 5 | $0.00006 | $0.00049 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
analyze 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 5d 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.
What it actually says
Analyze the social video/post at: $ARGUMENTS
Follow the analyze-social skill workflow:
- Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/analyze.py" "$ARGUMENTS"(warn the user the first run auto-installs tools and may take a few minutes). - Handle any
ERROR_CODE(e.g.NEEDS_LOGIN→ ask which browser they're logged into, re-run with--cookies-from-browser <browser>). - Read
manifest.json,meta.txt,transcript.txt, and view the frames from the bundle. - Produce the thorough breakdown defined in the skill's output template (header, TL;DR, full verbatim transcript with timestamps, on-screen text & visuals, verbatim caption, beat-by-beat, takeaway & intent, notable details), then stay open for follow-ups.
If $ARGUMENTS is empty, ask the user for a link or file path.
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.
- 5d ago First seen · 16 lines · 30 tokens per session scan A b5fe85b6986f
analyze is a command published in the GitHub repository Shivang0/social-vision (1 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 243 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
launch-meta-campaign
Launch a complete Meta Ads campaign — campaign, ad set, and ad(s) — built paused and ready to review. Use when the user wants a new Facebook/Instagram campaign.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
save
Save this conversation as a new or existing reusable context.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
duck-off
Turn off Rubber Duck mode and answer normally.