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 ayushozha/AdobePremiereProMCP --skill premiere-dialogue-cutgit clone --depth 1 https://github.com/ayushozha/AdobePremiereProMCPWrote 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/ayushozha/adobepremierepromcp/premiere-dialogue-cut)<a href="https://agentmods.dev/skills/ayushozha/adobepremierepromcp/premiere-dialogue-cut"><img src="https://agentmods.dev/badge/skills/ayushozha/adobepremierepromcp/premiere-dialogue-cut/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/ayushozha/adobepremierepromcp/premiere-dialogue-cut"><img src="https://agentmods.dev/badge/skills/ayushozha/adobepremierepromcp/premiere-dialogue-cut.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00746 |
| Opus 5 | $0.00032 | $0.00373 |
| Sonnet 5 | $0.00013 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
premiere-dialogue-cut 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premiere Dialogue Cut
Build an evidence-backed cut plan before touching the timeline. Favor natural pacing over maximum compression.
Required server profile
Start or restart the MCP server with MCP_TOOL_PROFILE=dialogue. The default standard profile also contains this workflow, but dialogue is the smaller dedicated surface.
Workflow
- Call
premiere_ping,premiere_get_project, andpremiere_get_timeline. Stop if the host, project, or target sequence is unavailable. - Resolve the active sequence index with
premiere_get_sequence_list. Before duplication, capture the source settings and a canonical timeline inventory: track counts, clip order, source-media paths, source in/out ranges, timeline start/end ranges, speed, and duration. Callpremiere_duplicate_sequence, re-read the list to identify exactly one new copy, and activate it withpremiere_set_active_sequence. Re-read the same canonical fields and require them to match while ignoring the clone name and sequence/clip identities. Do not compare sequence hashes across distinct sequences: the hash intentionally includes sequence and clip identity, so a valid clone has a different hash. Leave the source sequence untouched as the recovery boundary.premiere_snapshot_timelineandpremiere_save_sequence_versionmay record before/after audit data, but they cannot restore a whole sequence. - List the dialogue clips with
premiere_get_clips_on_track, then callpremiere_get_clip_infoto resolve each source-media path, source in/out range, speed, and timeline range. - Call
premiere_analyze_waveformonce per unique source path. Use its decoded-audiosilence_regions; the legacypremiere_detect_silencehost command only returns clip metadata and is not silence evidence. Stop if waveform analysis is unavailable or empty for a clip that should contain audio. - Intersect source silence with each used source range and map it to timeline time. Stop on reversed, retimed, or variable-frame-rate media unless that mapping can be verified. Keep 80–150 ms before speech, 120–250 ms after speech, and preserve longer rhetorical pauses unless the user asks for an aggressive cut.
- Show a proposed plan with edit count, removed duration, shortest retained pause, affected tracks, and protected markers before applying changes.
- Apply approved edits in reverse timeline order with
premiere_razor_clip,premiere_remove_clip_from_track, andpremiere_ripple_delete_gap, or usepremiere_ripple_trimwhen it expresses the same edit safely. - Re-read the timeline and sequence hash. Verify duration change, A/V sync, clip ordering, and that no edit overlaps protected markers.
What ships with it
1 file beside SKILL.md 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.
- 13d ago First seen · 31 lines · 65 tokens per session scan A b7ba1a24c06d
premiere-dialogue-cut is a skill published in the GitHub repository ayushozha/AdobePremiereProMCP (99 stars, last pushed 12d ago), licensed MIT. It adds 65 tokens to every session and 746 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
premiere-pro-mcp
Install, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues.
edit-premiere-project
Inspect, edit, verify, and export an open Adobe Premiere Pro project through the local Premiere MCP Bridge.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
agent-qa-testing
Agent davranis testi ve protokol uyumluluk dogrulamasi. Agent'larin tanimli rollerine uygun davranip davranmadigini assertion-based test'lerle olcer. Personality drift, role violation ve output kalite regresyonu tespit eder.