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 Poppify/poppify-claude-plugin --skill poppify-schedule-optimizergit clone --depth 1 https://github.com/Poppify/poppify-claude-pluginWrote 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/poppify/poppify-claude-plugin/poppify-schedule-optimizer)<a href="https://agentmods.dev/skills/poppify/poppify-claude-plugin/poppify-schedule-optimizer"><img src="https://agentmods.dev/badge/skills/poppify/poppify-claude-plugin/poppify-schedule-optimizer.svg" alt="Measured on agentmods" 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 | $0.00144 | $0.01056 |
| Opus 5 | $0.00072 | $0.00528 |
| Sonnet 5 | $0.00029 | $0.00211 |
| Haiku 4.5 | $0.00014 | $0.00106 |
Grade A, and why
poppify-schedule-optimizer 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 7d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scheduling for engagement & reach — the optimizer flow
Poppify tracks engagement per {day-of-week, hour} bucket from the account's REAL published posts (the same data behind the mobile calendar heatmap). publish_post exposes it — your job is to use it instead of scheduling blind.
Where the data comes from (so you can explain it honestly)
aggregates/time_slotsper user: avg engagement rate, reach, likes/comments/saves/shares, post count,bestPostType, and a performance tier per day×hour bucket — recomputed from published-post metrics at every sync.- Ranking is confidence-weighted (
ER × log2(samples+1) × reach factor), so one lucky post doesn't crown a slot. Two posts at 142% ER can still rank above ten posts at 2% — but say the sample size out loud when it's thin (postCount≤ 3). - All hours are UTC. Convert to the user's timezone when presenting, and say which timezone you're showing.
The flow
- After
get_resultreturnscomplete, callpublish_post({apiKey, postId})with no channelIds. The response carries BOTHavailableChannelsandrecommendedSlots. - Check
recommendedSlots.basis:"engagement_history"→ these are the account's own numbers. Present the top 2–3 like: "Your audience engages best Fridays around 19:00 UTC (avg ER 4.2% across 11 posts). Next window: Fri Jul 10.""platform_norms"→ no history yet. Say so: "No engagement history on this account yet, so these are general platform norms (Tue–Thu midday). They'll become YOUR numbers as posts accrue metrics." Don't oversell norms as personalized.
- Let the user pick channels (never auto-select) and a time:
- User says "best time" →
scheduledAt: "best"(auto-picks the top upcoming slot; response'spickedFromtells you which basis it used), or pass a specific slot'snextOccurrenceverbatim. - User picks their own time → schedule it, then read
slotAssessmentin the response. If the verdict says historically weak, surface it with the better alternative — advisory, one sentence, never re-schedule without being asked.
- User says "best time" →
- "Post now" (omit
scheduledAt) is always legitimate for time-sensitive content. For evergreen content, gently note when a top slot is < ~48h away: waiting usually beats posting into a dead zone.
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.
- 7d ago First seen · 49 lines · 144 tokens per session scan A 4d90b6da2aea
poppify-schedule-optimizer is a skill published in the GitHub repository Poppify/poppify-claude-plugin (0 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 1,056 once invoked, about $0.0007 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
lanshu-create-ai-presenter-video
Turn a topic or finished script plus an authorized adult presenter image into a complete, publish-ready AI presenter video. Use for new presenter videos and for continuing, revising, captioning, lip-sync repairing, or re-exporting an existing presenter-video job. Keep model and provider selection capability-based and…
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…
video-podcast-maker-factory
Use when the user wants to create their own custom narrated-video pipeline skill — a personal video-podcast-maker-xxx variant with their own TTS backend, visual style, and review gates. Forks the lite reference implementation. Do NOT trigger for making an actual video (use the user's existing variant) or for full…
travel-skill
A production guide for realistic travel-promotion videos that combine authorised real footage with AI-generated shots.