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 winLee1118/social-publisher-mcp --skill social-publishergit clone --depth 1 https://github.com/winLee1118/social-publisher-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/winlee1118/social-publisher-mcp/social-publisher)<a href="https://agentmods.dev/skills/winlee1118/social-publisher-mcp/social-publisher"><img src="https://agentmods.dev/badge/skills/winlee1118/social-publisher-mcp/social-publisher/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/winlee1118/social-publisher-mcp/social-publisher"><img src="https://agentmods.dev/badge/skills/winlee1118/social-publisher-mcp/social-publisher.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 | $0.00075 | $0.00496 |
| Opus 5 | $0.00037 | $0.00248 |
| Sonnet 5 | $0.00015 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
social-publisher 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Publisher
Use this skill to prepare, validate, and publish social media posts through the local social-publisher-mcp server.
Core Workflow
- Confirm the source content, target platforms, account names, media assets, title, tags, and schedule.
- Refuse to publish copyrighted, private, unsafe, or impersonating material unless the user owns it or clearly has permission.
- Call
list_platformsto verify dry-run/live status and available engines. - For live platforms, call
check_platform_authbefore preparing final publication. - Call
prepare_postand review warnings. Stop when media is missing, incompatible, or unexpectedly truncated. - Before live publishing, restate the exact platform, account, title, media file, tags, schedule, and whether it is public/draft.
- Call
publish_postonly after the user explicitly confirms that exact action. IncludeliveConfirmation.confirmed=trueand a conciseliveConfirmation.summaryof what the user approved. - Return the publish record id, platform results, and any platform URLs. Use
check_publish_statusfor follow-up checks.
Content Rules
- Preserve the user's core message while adapting title length, body length, tags, and media expectations by platform.
- Keep claims honest; do not invent performance, pricing, endorsements, availability, medical/legal/financial claims, or platform-specific guarantees.
- Default to dry-run for workflow tests unless the user explicitly asks for live publishing and confirms at action time.
- Prefer clearly labeled test content for live upload tests, such as "test upload, please ignore".
Live Publishing Safety
Live publishing transmits content to external platforms. Never call publish_post for live targets based only on a broad earlier intent like "test it" or "continue"; get action-time confirmation after showing the exact content and destination.
For Douyin through the vendored social-auto-upload CLI, read references/douyin-sau.md before live login, auth checks, or publishing.
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.
- 12d ago First seen · 33 lines · 75 tokens per session scan A 4d8ecf0c49cf
social-publisher is a skill published in the GitHub repository winLee1118/social-publisher-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 496 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…