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 MoonTzai/folderbridge-mcp --skill generated-video-reviewgit clone --depth 1 https://github.com/MoonTzai/folderbridge-mcpWrote 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/moontzai/folderbridge-mcp/generated-video-review)<a href="https://agentmods.dev/skills/moontzai/folderbridge-mcp/generated-video-review"><img src="https://agentmods.dev/badge/skills/moontzai/folderbridge-mcp/generated-video-review/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/moontzai/folderbridge-mcp/generated-video-review"><img src="https://agentmods.dev/badge/skills/moontzai/folderbridge-mcp/generated-video-review.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 | $0.00374 |
| Opus 5.5 | $0.00000 | $0.00150 |
| Sonnet 5.5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
generated-video-review 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
Generated Video Review
Review each generated take before upscale, subtitles or final assembly. Compare against the approved narration/storyboard/shot manifest, not against how impressive the clip looks in isolation.
Review order
- Semantic match: does the clip visibly support the spoken claim at the intended moment?
- Concept discrimination: if narration distinguishes A/B/C, are those differences actually visible without text?
- Continuity: recurring character, world, map topology, screen direction and symbolic grammar remain coherent where continuity is required.
- Causality/action: visible motion has a plausible start, connection, result and end state.
- Composition/readability: the intended subject/relation is visually dominant, not buried in effects.
- Model artifacts: anatomy, identity drift, unwanted text/UI, repeated blobs, broken geometry, frame duplication or obvious interpolation.
- Technical provenance: actual resolution, fps, frame count, duration, audio state and SHA match the job manifest.
Severity
- BLOCK: wrong meaning, missing explanatory evidence, contradiction with narration, severe continuity break, wrong provenance/resolution.
- RETAKE: meaning is basically right but shot execution, composition, motion or identity is not acceptable.
- TRIM/ASSEMBLY FIX: source take is good; only timing/cut point needs adjustment.
- PASS: semantically and technically usable.
Retake discipline
Retake the smallest failing unit. Do not regenerate upstream accepted shots merely to preserve a chain. If continuity requires a new starting image, derive it from an accepted take or explicitly approved asset rather than rerolling the whole sequence.
Final acceptance
Before assembly, every narration clause must map to at least one PASS visual event. Repeated footage must have an explicit narrative reason. No low-resolution TEST asset may enter a native-delivery path without an explicit upscale provenance record.
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 · 29 lines · 0 tokens per session scan A 82a9485a15dd
generated-video-review is a skill published in the GitHub repository MoonTzai/folderbridge-mcp (2 stars, last pushed 25d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 374 tokens. 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 2026-09-08.
Other skills, from other repositories
erga-mcp
Use immediately when a user shares a job-posting URL—including a bare link or chat preview—and when organizing recruiting records, evaluating career evidence, or proposing a truthful résumé update through Erga MCP.
mem0-cli
Mem0 CLI -- the command-line interface for mem0 memory operations. TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@mem0/cli", "mem0-cli", "pip install mem0-cli", "npm install -g @mem0/cli", or is running mem0 commands in a terminal/shell (mem0 add, mem0 search, mem0 list, mem0 get, mem0 init, mem0…
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
python-env
Setting up or installing into a Python environment. One rule applies whether or not you read the body - the environment belongs with the project, so create it inside the project directory (.venv) or let uv manage it, and never in a scratch directory like /tmp and never by forcing an install into the system…
mem0-remember
Stores a memory verbatim from user input with appropriate type classification and metadata. Use when the user says remember this, save this, store this, note that, or explicitly asks to record a decision, preference, convention, or learning.