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 AiAi-Mastermind/aiai-mastermind-tools-and-skills --skill facebook-personal-browsergit clone --depth 1 https://github.com/AiAi-Mastermind/aiai-mastermind-tools-and-skillsWrote 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/aiai-mastermind/aiai-mastermind-tools-and-skills/facebook-personal-browser)<a href="https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/facebook-personal-browser"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/facebook-personal-browser/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/aiai-mastermind/aiai-mastermind-tools-and-skills/facebook-personal-browser"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/facebook-personal-browser.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 | $0.00151 | $0.01500 |
| Opus 5.5 | $0.00060 | $0.00600 |
| Sonnet 5.5 | $0.00030 | $0.00300 |
| Haiku 4.5 | $0.00015 | $0.00150 |
Grade B, and why
facebook-personal-browser scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
FR="$(ls -d ~/.claude/skills/facebook-personal-browser ~/.codex/skills/facebook-personal-browser ~/.agents/skills/facebook-personal-browser 2>/dev/null | head -1)/bin/fb-read" How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your personal Facebook (read-only)
This is your real personal account. Look, don't touch. Meta's terms forbid automated data collection even on your own logged-in account. Meta enforces against speed and volume with checkpoints, feature blocks and restrictions, and publishes no safe rate. A restricted account costs far more than any research is worth. So:
- Research across groups and Instagram: use
muse-browser. That is Meta's own AI searching for you. - This skill: a few specific posts or pages, opened slowly.
Requires the aiai-agent-chrome kit, installed and running, with you signed in to Facebook inside the Agent Chrome window.
1. Before anything
- Load the
agent-chromeskill and follow it: your own tab,"$AC" pwonly,tab-closethendetach. Never send Facebook pages tojev-drive(it is for public sites only).AC="$HOME/.local/share/agent-chrome/bin/agent-chrome". - Check the sign-in: open
https://www.facebook.com/in your own tab and snapshot. A login form, or a URL containing/loginor/checkpoint, means signed out: stop and tell the owner."$AC" open https://www.facebook.com/opens a tab for them to sign in.- Never type credentials, handle a code, or solve a checkpoint.
- Stop everything on any checkpoint, "confirm it's you", "suspicious activity", "you're temporarily blocked" or "going too fast" screen. Close your tab and tell the owner. No more Facebook work that day.
2. Read a post: fb-read
FR="$(ls -d ~/.claude/skills/facebook-personal-browser ~/.codex/skills/facebook-personal-browser ~/.agents/skills/facebook-personal-browser 2>/dev/null | head -1)/bin/fb-read"
"$FR" "https://www.facebook.com/groups/<group>/permalink/<post id>/" --comments 10 --json
- It opens the post in its own tab and reads the snapshot. It never clicks, types or presses a key, so it cannot like, comment or join.
- It returns
author, the post text (answer_markdown, with the first comments appended),reactionsas shown, andcomments(who and when, plus the text). - Status
checkpointmeans follow the stop rule above.not_found: the post is unavailable to your account.ui_changed: not a post permalink, or Facebook changed its page.error: bad URL (only plainhttps://www.facebook.com/...post links are accepted; redirectorl.phplinks are refused) or the driver failed.not_installed/not_running: run"$AC" doctor. - The post date is often not exposed in the snapshot. Take it from Muse's citation or from the comment times.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 80 lines · 151 tokens per session scan B 967119c8baa4
facebook-personal-browser is a skill published in the GitHub repository AiAi-Mastermind/aiai-mastermind-tools-and-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 151 tokens to every session and 1,500 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other skills, from other repositories
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
apply
A browser-based job application workflow for submitting applications through services such as Ashby, Greenhouse, Lever, and Hacker News. It uses prepared candidate information, answers, job links, and cover letters.
dr-fanout
Fan one deep-research prompt out to several external LLMs at once through a logged-in browser, then collect the reports, archive the originals and synthesize a consensus. Use at the final stage of a research protocol, instead of hand-pasting one prompt into N sites. Triggers: "/dr-fanout", "fan out the DR"…
cv-outreach
A daily workflow for carrying out scheduled outward-facing tasks, such as event registrations, messages to organisers, and public posts. It uses a browser identity carefully so actions are made from the intended account.
social-daily
A workflow for publishing prepared content to Facebook, X, Telegram, Threads, and Instagram. It uses a shared queue so posts for different platforms can be tracked together.
fb-reply
Read who commented on recent Facebook posts and publish personalized replies through the real logged-in Chrome tab, draft-first, with a daily cap and a minimum gap between replies. Triggers: "/fb-reply", "reply to my facebook comments".