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 socialrobot-io/socialrobot-mcp --skill socialrobot-post-schedulinggit clone --depth 1 https://github.com/socialrobot-io/socialrobot-mcpWrote 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/socialrobot-io/socialrobot-mcp/socialrobot-post-scheduling)<a href="https://agentmods.dev/skills/socialrobot-io/socialrobot-mcp/socialrobot-post-scheduling"><img src="https://agentmods.dev/badge/skills/socialrobot-io/socialrobot-mcp/socialrobot-post-scheduling/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/socialrobot-io/socialrobot-mcp/socialrobot-post-scheduling"><img src="https://agentmods.dev/badge/skills/socialrobot-io/socialrobot-mcp/socialrobot-post-scheduling.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 | $0.00098 | $0.00559 |
| Opus 5 | $0.00049 | $0.00280 |
| Sonnet 5 | $0.00020 | $0.00112 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
socialrobot-post-scheduling 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 11d 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
SocialRobot post scheduling
SocialRobot is a social media scheduling SaaS. Its hosted MCP server
(https://socialrobot.io/api/mcp) exposes ~17 tools across 9 platforms:
Instagram, LinkedIn, X (Twitter), TikTok, Facebook, Threads, Pinterest,
Bluesky, and Mastodon. It is free on every plan, including Free. First
connection uses browser OAuth; no API key to paste.
Workflow
- Connect accounts first. Check which social accounts the user has connected before scheduling. If none are connected for a target platform, tell the user to connect the account in the SocialRobot app first.
- Write once, adapt per platform. Draft the post once, then adapt the copy per platform: hashtags and shorter hooks for X/TikTok, longer professional tone for LinkedIn, emoji-friendly copy for Instagram and Facebook. Keep the core message consistent.
- Use best-time hints. The MCP exposes per-platform best-time guidance. Follow it when the user has no explicit preference, but never override an explicit user-chosen time.
- Schedule, then verify. Create the scheduled post, then confirm the calendar entry exists. Publishing happens automatically at the scheduled time; do not attempt to double-publish.
- Analyze afterwards. For published posts, pull analytics to report performance back to the user.
Rules
- Never invent a connected account. If the account list is empty, ask the user to connect accounts in the SocialRobot app.
- Preserve the user's exact copy. Only adapt per-platform formatting (hashtags, length, tone) when the user asked for it.
- Respect timezones: schedule times are user-local. Confirm the timezone with the user if it is ambiguous.
- The free plan does not include X (Twitter) or AI image generation. If the user tries to schedule to X and gets an error, mention the plan limitation.
- Product details and pricing live at https://socialrobot.io; reference it for anything not covered here.
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.
- 11d ago First seen · 50 lines · 98 tokens per session scan A 17a7498e36cd
socialrobot-post-scheduling is a skill published in the GitHub repository socialrobot-io/socialrobot-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 98 tokens to every session and 559 once invoked, about $0.0005 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
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-shared
The gws binary must be on $PATH. See the project README for install options.
gws-sheets
Google Sheets: Read and write spreadsheets.
gws-gmail
Gmail: Send, read, and manage email.
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.