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/ihuzaifashoukat/splicedeckWrote 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/plugins/ihuzaifashoukat/splicedeck/splicedeck)<a href="https://agentmods.dev/plugins/ihuzaifashoukat/splicedeck/splicedeck"><img src="https://agentmods.dev/badge/plugins/ihuzaifashoukat/splicedeck/splicedeck/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/plugins/ihuzaifashoukat/splicedeck/splicedeck"><img src="https://agentmods.dev/badge/plugins/ihuzaifashoukat/splicedeck/splicedeck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
splicedeck 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 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.
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.
What it actually says
{
"name": "splicedeck",
"displayName": "splicedeck",
"version": "0.0.0",
"description": "Drive splicedeck from Claude Code: cut a deliverable, carve vertical clips, recover from a typed refusal in one turn, and change the codebase itself.",
"author": {
"name": "Huzaifa Shoukat",
"email": "[email protected]",
"url": "https://github.com/ihuzaifashoukat"
},
"homepage": "https://github.com/ihuzaifashoukat/splicedeck#readme",
"repository": "https://github.com/ihuzaifashoukat/splicedeck",
"license": "Apache-2.0",
"keywords": [
"video-editing",
"ffmpeg",
"mcp",
"captions",
"motion-graphics",
"local-first"
],
"skills": "./.claude/skills/"
}
What it installs
The manifest is a name and a version. 4 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 389 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
- 1mo ago First seen · 24 lines scan A 35d63534c1a6
splicedeck is a plugin published in the GitHub repository ihuzaifashoukat/splicedeck (4 stars, last pushed 2mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
rudder
Maintain a device-local spec from coding-session intent, then generate focused unit tests with your existing coding agent.
herdrpowers
Multi-pane development framework for herdr: structured skills and multi-phase workflows that delegate implementation, testing, and review to idle sibling agent panes instead of in-process subagents.
code-oz
Enforced SDLC gates + cross-family review for AI coding agents. Discovers and invokes the code-oz engine; the binary is the only writer of gates, events, and reviews.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.