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 DamianoTobasco/sync-socials-agent --skill social-publishinggit clone --depth 1 https://github.com/DamianoTobasco/sync-socials-agentWrote 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/damianotobasco/sync-socials-agent/social-publishing)<a href="https://agentmods.dev/skills/damianotobasco/sync-socials-agent/social-publishing"><img src="https://agentmods.dev/badge/skills/damianotobasco/sync-socials-agent/social-publishing/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/damianotobasco/sync-socials-agent/social-publishing"><img src="https://agentmods.dev/badge/skills/damianotobasco/sync-socials-agent/social-publishing.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 | $0.00052 | $0.01382 |
| Opus 5.5 | $0.00021 | $0.00553 |
| Sonnet 5.5 | $0.00010 | $0.00276 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
social-publishing 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 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.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Socials publishing
This plugin declares the hosted Sync Socials connector, which the user must
connect and authenticate in Claude before its tools can operate. Use the
available Sync Socials MCP tools. Tool names below may have a client-added
prefix; match the syncsocials_ name. Discover the current tool schemas before
calling them. Do not register another MCP server or construct a REST or API-key
workaround when this connector is unavailable.
Establish the workspace
Call syncsocials_get_workspace to check the workspace identity, timezone,
capabilities, and allowances. For targeted drafts, schedules, or publishing, call
syncsocials_list_connections and use only the returned connected account IDs.
Do not infer that a destination is available from its platform name. When more
than one account matches and the user has not selected one, ask them to choose.
Use syncsocials_list_posts to inspect the queue or locate a requested post.
Facebook publishing targets Facebook Pages, not personal profiles. Instagram publishing requires a business or creator account linked to a Facebook Page and an image or video; text-only Instagram posts are unsupported. Use each platform's own returned account ID, including when Facebook and Instagram share a linked Page. If a destination is missing or needs reauthorization, direct the user to Sync Socials Connections to connect or reconnect, allow publishing, and select the correct Page or linked Instagram account. Recheck the connection before targeting it; app approval does not replace the customer's account consent.
If the tools are absent or authentication fails, explain that a connected Sync Socials workspace is required. In Chat or Cowork, direct the user to the plugin's Connectors tab. This bundle supports Claude apps and Cowork; direct Claude Code OAuth is unsupported. Use the setup guide for the supported connection flow. Installing the plugin alone does not authenticate the workspace. Do not claim that a directory listing or a working public sign-in flow exists unless verified. Never request OAuth client secrets, access tokens, or social passwords in conversation. Stop on missing access or quota errors and explain the specific remedy returned by the service.
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 Changed · +11 lines 589738c46c8a
- 12d ago First seen · 102 lines · 52 tokens per session scan A 1b7a7c524c2e
social-publishing is a skill published in the GitHub repository DamianoTobasco/sync-socials-agent (0 stars, last pushed 8d ago), licensed MIT. It adds 52 tokens to every session and 1,382 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
media-mcp
Social media at your fingertips. Fetch tweets, transcribe videos with per-token confidence, extract frames at exact timestamps, download Instagram posts — from any MCP client. 30 tools across Twitter/X, YouTube, Instagram, and video processing. All transcription runs locally via Whisper with uncertainty markers so…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
apitap
ApiTap gives AI agents cheap access to web data through three layers.