premiere-mcp-editor-cn: Skill for Codex

.codex/skills/premiere-agent-closed-loop/SKILL.md

premiere-agent-closed-loop is a skill for Codex from sylphiette269/premiere-mcp-editor-cn. It costs 40 tokens per session (379 once invoked), scanned A, original, MIT.

A workflow for building video-editing agents in premiere-mcp, a tool system for working with Adobe Premiere projects. It requires research, planning, write verification, and independent review before reporting success.

In plain words
What is it for?
Adding task scenarios, style-driven video assembly, read-back checks after important writes, critic reviews, and structured error reports to a Premiere editing agent.
Why use it?
It reduces the risk of an agent assembling the wrong edit, claiming a write worked when it did not, or hiding an unstructured failure.

Skill for Codex

Written for Codex: installed under .codex/.

This is sylphiette269/premiere-mcp-editor-cn's own configuration. It tells Codex how to work on premiere-mcp-editor-cn itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything premiere-mcp-editor-cn configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sylphiette269/premiere-mcp-editor-cn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sylphiette269/premiere-mcp-editor-cn/main/.codex/skills/premiere-agent-closed-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sylphiette269/premiere-mcp-editor-cn

Made for: Codex.

Wrote 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.

agentmods badge for premiere-agent-closed-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/sylphiette269/premiere-mcp-editor-cn/premiere-agent-closed-loop/github.svg)](https://agentmods.dev/skills/sylphiette269/premiere-mcp-editor-cn/premiere-agent-closed-loop)
Your own site
<a href="https://agentmods.dev/skills/sylphiette269/premiere-mcp-editor-cn/premiere-agent-closed-loop"><img src="https://agentmods.dev/badge/skills/sylphiette269/premiere-mcp-editor-cn/premiere-agent-closed-loop/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.

agentmods 80×15 button for premiere-agent-closed-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/sylphiette269/premiere-mcp-editor-cn/premiere-agent-closed-loop"><img src="https://agentmods.dev/badge/skills/sylphiette269/premiere-mcp-editor-cn/premiere-agent-closed-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00379
Opus 5 $0.00020 $0.00189
Sonnet 5 $0.00008 $0.00076
Haiku 4.5 $0.00004 $0.00038

Measured 12d ago against content hash 5242b6592068, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

premiere-agent-closed-loop 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 12d 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.

.codex/skills/premiere-agent-closed-loop/SKILL.md · 47 lines

What it actually says

Premiere Agent Closed Loop

Overview

This skill captures the repo-local workflow for turning premiere-mcp into a closed-loop editing agent instead of a loose collection of tools.

When to Use

  • Adding or changing agent orchestration behavior
  • Introducing task scenarios such as viral_style or reference_video
  • Adding post-write verification or critic-style review gates
  • Standardizing tool/runtime errors for programmatic recovery

Required Workflow

  1. Classify the request into an explicit scenario first.
  2. Produce a structured plan with prerequisites, success criteria, and per-step failure behavior.
  3. Enforce the research gate before any style-driven assembly work.
  4. Verify important write operations with read-back comparison.
  5. Run an independent critic before reporting success.
  6. Emit a structured failure report when the loop aborts.

Guardrails

  • Do not allow build_timeline_from_xml on the agent path while it is marked disabled.
  • Do not let viral_style or reference_video skip research and go straight to assembly.
  • Do not treat ok:true or success:true as completion without verification and critic results.
  • Do not leave failures as free-form strings only; keep error_code and retryable available for runtime decisions.

Common Mistakes

  • Folding planning, execution, validation, and review into one opaque step
  • Using existence-only checks where the task needs value comparison
  • Letting the execution layer self-certify success without a critic pass
  • Forgetting to preserve fallback guidance for disabled tools
Changes

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.

  1. 12d ago First seen · 47 lines · 40 tokens per session scan A 5242b6592068

Subscribe to this mod's changes

premiere-agent-closed-loop is a skill published in the GitHub repository sylphiette269/premiere-mcp-editor-cn (7 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 379 once invoked, about $0.0002 per session on Opus 5. 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.

Related

Other skills, from other repositories

gpt-image-2-prompt-architect

Research real GPT Image 2 prompt examples and turn rough image ideas into structured prompt packs, reference-image edit instructions, product visuals, layouts, and debugging loops. Use for prompt search, prompt rewriting, ecommerce images, readable text, posters, social creatives, character sheets, storyboards, or…

gpt-img-2/image3-prompt-mcp · 84 tokens

seedance-video-prompt-architect

Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot storyboards, product ads, fashion clips, cinematic scenes, dialogue, or creator…

gpt-img-2/cdance-prompt-mcp · 81 tokens

china-video-prompt-architect

Turn rough China AI video ideas into structured English or Chinese prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, reference-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for…

gpt-img-2/chinavideoai-prompt-mcp · 83 tokens

opensora-video-prompt-architect

Turn rough video ideas into structured OpenSora prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for unrelated models, account support, or…

gpt-img-2/opensora2-prompt-mcp · 79 tokens

seevido-video-prompt-architect

Turn rough video ideas into structured English or Chinese prompt packs, reference-aware sequences, continuity rules, and focused debugging loops. Use for text-to-video, image-to-video, reference-to-video, video-to-video, product clips, cinematic scenes, or multi-shot work; do not use for account support, live model…

gpt-img-2/seevido-prompt-mcp · 79 tokens

see-dance-2-video-prompt-architect

Turn rough video ideas into structured English or Chinese Seedance-oriented prompt packs, exact reference bindings, shot sequences, and focused debugging loops. Use for text-to-video, image-to-video, multimodal reference, product clips, cinematic scenes, transitions, or loops; do not use for account support, live…

gpt-img-2/see-dance-2-prompt-mcp · 81 tokens