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.
git 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/commands/poppify/poppify-claude-plugin/verify-render)<a href="https://agentmods.dev/commands/poppify/poppify-claude-plugin/verify-render"><img src="https://agentmods.dev/badge/commands/poppify/poppify-claude-plugin/verify-render/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/commands/poppify/poppify-claude-plugin/verify-render"><img src="https://agentmods.dev/badge/commands/poppify/poppify-claude-plugin/verify-render.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 | $0.00027 | $0.00434 |
| Opus 5.5 | $0.00011 | $0.00174 |
| Sonnet 5.5 | $0.00005 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
verify-render 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Capability gate first.** This is an OPTIONAL deep check that needs a local shell with `ffmpeg` + `ffprobe` + `curl`. If your client has no Bash/shell tool (e.g. Claude Desktop, web), STOP — you can't run it. Just give What it actually says
The user wants to verify a Poppify render before shipping the URL. Args: $ARGUMENTS
Capability gate first. This is an OPTIONAL deep check that needs a local shell with ffmpeg + ffprobe + curl. If your client has no Bash/shell tool (e.g. Claude Desktop, web), STOP — you can't run it. Just give the user the videoUrl and, if they've reported a problem, use /poppify:troubleshoot (pure MCP-tool reasoning, no shell). Only proceed if which ffprobe ffmpeg curl succeeds.
Invoke the poppify-render-debug skill and follow it:
-
If args is a
sessionId, callget_result({ sessionId, apiKey })to fetch thevideoUrl. If args is already a URL, use it directly. -
Download the MP4 to
/tmp/poppify-verify/render.mp4. -
Run
ffprobe -v error -print_format json -show_streams -show_formatand check:- Video stream present (h264, 720x1280, ~24fps)
- Audio stream present (aac)
- Duration matches the sum of per-slide durations (text-length-driven; voiceover/live clips play in full) within ±1s
-
Extract sample frames at 1fps and visually verify:
- Caption text appears on intended slides
- Caption color matches request
- Caption position matches
textAnimation - Image content matches the slide's
voiceoverShort
-
Produce a Markdown verdict table. Green checks → hand the URL to the user (signed URL valid ~7 days). Red checks → surface the specific failure and recommend the corresponding
/poppify:troubleshootpath. -
Clean up
/tmp/poppify-verify/when done.
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.
- 1mo ago First seen · 30 lines · 27 tokens per session scan A 5ab9cc4733e6
verify-render is a command published in the GitHub repository Poppify/poppify-claude-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 434 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
mutate
Run mutation testing to verify test quality. Builds a custom mutation tool or uses an existing framework, runs mutations, and reports the mutation score with surviving mutants.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
test-audit
Use when writing, reviewing, or pruning tests. Three modes, one value bar: a four-question gate before any new test is written, a focused audit of one scope, and a campaign over a whole repo or subsystem that removes the least useful tests under a coverage guard. Every delete, merge, or repair carries written evidence…
partition-dev
Derive test cases from Z specification using TTF testing tactics.