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-troubleshootgit 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-troubleshoot)<a href="https://agentmods.dev/skills/poppify/poppify-claude-plugin/poppify-troubleshoot"><img src="https://agentmods.dev/badge/skills/poppify/poppify-claude-plugin/poppify-troubleshoot/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/poppify/poppify-claude-plugin/poppify-troubleshoot"><img src="https://agentmods.dev/badge/skills/poppify/poppify-claude-plugin/poppify-troubleshoot.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 | $0.00000 | $0.03783 |
| Opus 5.5 | $0.00000 | $0.01513 |
| Sonnet 5.5 | $0.00000 | $0.00757 |
| Haiku 4.5 | $0.00000 | $0.00378 |
Grade A, and why
poppify-troubleshoot scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If `videoUrl` returned but the URL doesn't open: the URL has expired and Poppify doesn't persist videos beyond the ~7-day TTL (cost-control). Re-`render` charges seeds again. Tell the user to save the file within the win How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Poppify render troubleshooting
Find the symptom that matches, then take the suggested action. Most root causes here trace to schema drift, library-asset state, or text/duration mismatches — not random renderer failures.
Symptom → Root cause → Action
"The live-motion slide has no sound"
Most likely: the clip genuinely has no audio stream. Veo 3.1 always generates audio, but Seedance and Kling are video-only — check which provider rendered it (account {default_provider} / get_capabilities.pricing.live_motion.availableModels). A video-only provider falls back to the ElevenLabs path, so that slide is silent unless you attach narration.
Also check: in a same-image run, several slides share one clip at different offsets and the audio is taken once, from the slide that starts the run. Later slides in that run are silent by design.
Not the cause any more: the composer used to strip the track with -an. It no longer does — VideoGenerator extracts the clip's audio and mixes it through the voiceover path.
"Two voices are talking over each other on one slide"
Root cause: a live clip's audio now REPLACES a generated voiceover on the same slide, so this shouldn't happen — if it does, the voiceover was attached to a different slide number than the live clip.
Action: get_session view:"plan" and confirm the voiceoverSlides index matches the slide carrying motionMode:"live". Never budget generate {narration} for a live slide; its audio is already there.
"No audio in the finished video"
Most likely: library audio asset was attached but resolvedUrl ended up empty (renderer can only download URLs, not asset IDs).
Action: get_session does NOT return a session object — it returns status, videoUrl, signedVideoUrl, price, voiceover, slideCount, errorMessage. For audio state call get_session({sessionId, view:"plan"}) and check the resolved soundtrack. If null/empty:
search({apiKey, music:{}}) // get fresh assetIds
edit_session({sessionId, commands:[{patch:{audio: { source: "library", assetId: <new id> }}}]})
render({ sessionId, apiKey }) // re-render (seeds re-charged)
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.
- today Changed · +10 lines c29a0e7ddf02
- 11d ago Changed · +5 lines 7125d9fc910d
- 17d ago Changed · +6 lines dd4548f297e9
- 24d ago Changed 73646c849c28
- 1mo ago Changed · +2 lines 8ff6eb1cfd76
- 1mo ago Changed · -2 lines 392fe5856710
- 2mo ago First seen · 149 lines · 0 tokens per session scan A 9637c7939c70
poppify-troubleshoot is a skill published in the GitHub repository Poppify/poppify-claude-plugin (0 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,783 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
poppify-troubleshoot compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| poppify-troubleshootPoppify/poppify-claude-plugin | Skill | 0 | yesterday | MIT | A | 0 | Claude Code |
| tidewave-integrationoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 38 | Claude Code |
| video-podcast-maker-liteAgents365-ai/video-podcast-maker | Skill | 1.7k | 1mo ago | MIT | A | 96 | Claude Code |
| create-shortDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 58 | Claude Code |
| generate-clipDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 32 | Claude Code |
| anti-patternsavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 59 | Claude Code |
| add-transitionsDojoCodingLabs/remotion-superpowers | Skill | 157 | 8d ago | MIT | A | 39 | Claude Code |