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/KyaniteLabs/kinocutWrote 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/kyanitelabs/kinocut/gemini-extension)<a href="https://agentmods.dev/plugins/kyanitelabs/kinocut/gemini-extension"><img src="https://agentmods.dev/badge/plugins/kyanitelabs/kinocut/gemini-extension/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/kyanitelabs/kinocut/gemini-extension"><img src="https://agentmods.dev/badge/plugins/kyanitelabs/kinocut/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kinocut 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 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.
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": "kinocut",
"version": "1.16.5",
"description": "Guardrailed local video editing: trim, caption, reformat for Shorts and check quality with FFmpeg on your own machine.",
"mcpServers": {
"kinocut": {
"command": "uvx",
"args": [
"kinocut==1.16.5"
]
}
}
}
What ships with it
49 files beside gemini-extension.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.
- assets/BRANDING.md 948 B
- assets/CHAKRA-PETCH-OFL.txt 4.3 KB
- assets/kinocut-hero.webp 59 KB
- assets/kinocut-wordmark.svg 1.3 KB
- assets/og.jpg 112 KB
- examples/agent_cookbook.py 2.3 KB runs code
- examples/agent_prompts/podcast_clip.md 3.1 KB
- examples/agent_prompts/product_demo_video.md 5.0 KB
- examples/agent_prompts/tiktok_captioned_clip.md 4.2 KB
- examples/claude_mcp_config.json 126 B
- examples/pip_install_config.json 98 B
- examples/product-matte/layers.json 523 B
- examples/product-matte/README.md 1.6 KB
- examples/python/shorts_workflow.py 5.2 KB runs code
- examples/README.md 1004 B
- examples/repurpose_current_tools_demo.py 4.9 KB runs code
- examples/workflows/captioned-vertical-short/job.json 933 B
- examples/workflows/captioned-vertical-short/README.md 2.3 KB
- scripts/annotate-pytest-failures.py 3.1 KB runs code
- scripts/apply_public_release_cutover.py 7.5 KB runs code
- scripts/audit_scores.py 10 KB runs code
- scripts/audit-runtime-allocation.py 11 KB runs code
- scripts/benchmark-runtime-optimizations.py 5.3 KB runs code
- scripts/build-mcpb.py 11 KB runs code
- scripts/ci_scope.py 1.5 KB runs code
- scripts/collect_usage_metrics.py 5.0 KB runs code
- scripts/forgejo_sync.py 24 KB runs code
- scripts/generate_golden_pack.py 7.9 KB runs code
- scripts/git-professional-audit.sh 3.0 KB runs code
- scripts/git-workspace-cleanup.sh 976 B runs code
- scripts/github-pr-monitor.py 6.4 KB runs code
- scripts/golden_path_timings.py 8.1 KB runs code
- scripts/golden_path.py 12 KB runs code
- scripts/kinocut-pending.py 9.1 KB runs code
- scripts/make_g004_fixtures.py 3.1 KB runs code
- scripts/mcpb_production_pack.py 11 KB runs code
- scripts/mcpb/__init__.py 45 B runs code
- scripts/mcpb/defaults.py 445 B runs code
- scripts/mcpb/errors.py 174 B runs code
- scripts/mcpb/manifest.py 1.5 KB runs code
- scripts/mcpb/model.py 11 KB runs code
- scripts/mcpb/supply_chain.py 21 KB runs code
- scripts/pip_audit_allowlist.txt 482 B
- scripts/repin_marketplaces.sh 4.3 KB runs code
- scripts/repo-readiness-audit.py 12 KB runs code
- scripts/secret_scan_allowlist.txt 2.6 KB
- scripts/secret_scan.py 11 KB runs code
- scripts/verify_onboarding_release.py 30 KB runs code
- scripts/verify_published_claims_live.py 4.1 KB runs code
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 93f57ece7b0c
- 3d ago Changed 550b3a503af3
- 4d ago Changed cbb07749f32a
- 6d ago First seen · 14 lines scan A 2d17bac9e476
kinocut is a plugin published in the GitHub repository KyaniteLabs/kinocut (223 stars, last pushed today), 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 2026-10-22.
Other plugins, from other repositories
before-you-build
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.
mc-agent-toolkit
Monte Carlo Agent Toolkit — data observability skills and enforcement hooks for AI coding agents.
kage
Kage manages your memory and agents. It briefs and runs agents in isolated git worktrees for a single run or a multi-wave goal, re-runs the checks itself instead of trusting the agent's report, and remembers what it learns so each brief is smarter than the last.
mosaic-bridge
Mosaic Bridge — Unity MCP assistant agents for scene building, shader creation, and session continuity.
collate
A plugin that provides an end-to-end workflow for OCR and proofreading historical Chinese documents. OCR turns scanned page images into editable text.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.