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 JackVitick/socialync-mcp --skill weekly-what-workedgit clone --depth 1 https://github.com/JackVitick/socialync-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/jackvitick/socialync-mcp/weekly-what-worked)<a href="https://agentmods.dev/skills/jackvitick/socialync-mcp/weekly-what-worked"><img src="https://agentmods.dev/badge/skills/jackvitick/socialync-mcp/weekly-what-worked/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/jackvitick/socialync-mcp/weekly-what-worked"><img src="https://agentmods.dev/badge/skills/jackvitick/socialync-mcp/weekly-what-worked.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 | $0.00093 | $0.00888 |
| Opus 5.5 | $0.00037 | $0.00355 |
| Sonnet 5.5 | $0.00019 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
weekly-what-worked 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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly review: what worked, what to post next
The review only reads data, so it needs no approval. Anything it leads to that publishes goes through the consent rule in the schedule-social-post skill.
Before you start
list_profiles. If the user has several profiles, ask which one, or review each separately.- Analytics are on paid Socialync plans. If
get_analyticsreturns a plan error or no data, say so in one line and offer the parts that still work: failed posts and next week's calendar. - Socialync collects analytics for TikTok, YouTube, Instagram, Facebook, Threads and Bluesky. X and LinkedIn have no numbers here, and Bluesky reports engagement without views. Say this when those platforms matter to the user.
Pull the data
get_analyticswithperiod: "week"andbreakdown: "by_platform". Useperiod: "month"if the user asks for a monthly view. The response compares against the previous period of the same length.get_top_postswithsort: "engagement"andlimit: 10. Use each post's date to keep to the period you are reviewing.get_top_postswithsort: "recent"andlimit: 20to see every recent post, including the weak ones.get_post_historyfor anything that failed this week, with its reason.get_scheduled_postsfor what is already queued for the next 7 days.
Write the review
Keep it short enough to read in a minute.
- The week in three lines: total views, engagement and followers with the change against last week, and the platform that moved most in each direction.
- Top 3 posts: platform, first line, views, engagement rate, status. Then what they share. Look at format (video, image, text), the type of hook, length, topic, day and time posted. Name the pattern only if at least two of the three show it.
- Bottom 3 posts with the same fields. A post with status
no_datahas no numbers yet. Leave it out of this list. - Failures: each failed post with its plain reason and the fix. For
reconnect, name the account to reconnect in Socialync Settings. - Next week: days with nothing scheduled.
- Three to five ideas for next week, each tied to a top post: "Your Tuesday how-to clip got 4 times your usual views. Make another how-to on [topic]."
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.
- 3d ago First seen · 57 lines · 93 tokens per session scan A ec25a01aa834
weekly-what-worked is a skill published in the GitHub repository JackVitick/socialync-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 93 tokens to every session and 888 once invoked, about $0.0004 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 2026-10-13.
Other skills, from other repositories
platform-reference
Complete reference for all 15 BulkPublish platforms — post types, media requirements, required fields, character limits, and platformSpecific options. ALWAYS consult before creating posts.
schedule-post
Create, schedule, or publish social media posts via BulkPublish MCP. Use when the user wants to post to social media.
check-quota
Check BulkPublish plan limits and current usage. Use when the user asks about their plan, limits, or remaining quota.
get-analytics
Pull analytics, engagement metrics, and performance data from BulkPublish. Use when the user asks about post performance or engagement.
manage-channels
List connected social media channels and check what the caller may do with them in BulkPublish. Use when the user asks about their connected accounts.
media-library
Upload images and video to BulkPublish and browse the media library, so files can be attached to posts. Use when the user wants to add or find media.