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 tang-vu/social-posting-skills --skill post-facebookgit clone --depth 1 https://github.com/tang-vu/social-posting-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/tang-vu/social-posting-skills/post-facebook)<a href="https://agentmods.dev/skills/tang-vu/social-posting-skills/post-facebook"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-facebook/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/tang-vu/social-posting-skills/post-facebook"><img src="https://agentmods.dev/badge/skills/tang-vu/social-posting-skills/post-facebook.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 | $0.00009 | $0.01843 |
| Opus 5 | $0.00005 | $0.00922 |
| Sonnet 5 | $0.00002 | $0.00369 |
| Haiku 4.5 | $0.00001 | $0.00184 |
Grade A, and why
post-facebook 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 12d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Facebook Posting Skill
Platform Overview
Facebook has 3B+ monthly active users. Best for community building, local audiences, and Facebook Groups. Organic page reach has declined, but Groups and personal profiles still drive engagement.
AI Content Rules (2025)
Meta requires mandatory "AI-generated" labels for synthetic content. Bot-generated repetitive content is actively targeted and penalized.
- AI-assisted content must be labeled as such
- Duplicate content posted by bot networks faces crackdown
- Accounts using spam tactics lose monetization eligibility
- AI labels apply to both images and text content
Platform Constraints
- Character Limit: 63,206 characters (but shorter performs better)
- Media: Images, videos, stories, reels, polls, events
- Links: Rich preview cards (but reduce organic reach)
- Groups: Best distribution channel on Facebook
- Hashtags: Minimal impact on reach (use 1-2 max or skip)
- Reels: Short-form video gets preferential treatment in discovery
Link Placement Strategy
DEFAULT: Put links in the FIRST COMMENT, not in the post body.
- Facebook's algorithm deprioritizes posts with external links in the body
- Native content (text, images, videos) without links gets significantly more reach
- Best strategy: Post engaging text-only content, then add the link as the first comment
- If you must include a link in the body, add substantial commentary around it
- Links to YouTube are especially penalized -- upload videos natively instead
Posting Steps (Browser Automation)
- Navigate to
https://www.facebook.com/ - Wait for the home page to load (must be logged in)
- Click on the "What's on your mind?" composer box
- Wait for the composer to expand
- Type the post content (ASCII English only)
- Click "Post" button
- Verify post appears on the timeline
- Immediately comment on your own post with the link (if applicable)
Posting to a Group
- Navigate to
https://www.facebook.com/groups/{group_id}/ - Click on the "Write something..." composer
- Type content
- Click "Post"
- Note: Post may show as "Pending admin approval" — this is normal for many groups
- After approved, add a comment with your link
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.
- 12d ago First seen · 206 lines · 9 tokens per session scan A 044e3b0bef1d
post-facebook is a skill published in the GitHub repository tang-vu/social-posting-skills (9 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 1,843 once invoked, about $0.0000 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 skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
accessibility-tester
Professional Accessibility Tester Expert skill. Implement robust test suites and automated quality checks for modern web/mobile applications.