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-look-effectsgit 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-look-effects)<a href="https://agentmods.dev/skills/ayushozha/adobepremierepromcp/premiere-look-effects"><img src="https://agentmods.dev/badge/skills/ayushozha/adobepremierepromcp/premiere-look-effects/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-look-effects"><img src="https://agentmods.dev/badge/skills/ayushozha/adobepremierepromcp/premiere-look-effects.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 27 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00056 | $0.00498 |
| Opus 5 | $0.00028 | $0.00249 |
| Sonnet 5 | $0.00011 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
premiere-look-effects 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.
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Premiere Look Effects
Discover capabilities from the host and test a look on one representative clip before batching it.
Required server profile
Start or restart the MCP server with MCP_TOOL_PROFILE=effects for the smallest dedicated surface. The default standard profile also contains this skill's verified discovery, attachment, parameter-update, and readback tools.
Workflow
- Inspect the project, timeline, installed effects, and current clip effect chain. Resolve the active sequence index, call
premiere_duplicate_sequence, verify exactly one new copy, and activate it withpremiere_set_active_sequence. Leave the source sequence untouched as the recovery boundary. - Record the current chain with
premiere_get_clip_effectsand the sequence hash. Usepremiere_snapshot_timelineorpremiere_save_sequence_versiononly as optional audit records; neither restores a whole sequence. - Build a minimal ordered recipe using only display names returned by
premiere_get_installed_effects. - Apply one effect at a time with
premiere_apply_video_effect. Require a public-DOM component-count increase and the attached component name. - Set only properties actually exposed by that component with
premiere_set_effect_parameter; read the chain and values back before continuing. - Test the recipe on one representative clip. If application or parameter readback fails, stop, reactivate the untouched source sequence, and report the failed duplicate for inspection; do not attempt an unverified component removal or undo. After approval, repeat the same verified steps on additional clips and stop on the first mismatch.
Guardrails
- Never assume an effect display name exists; confirm it with
premiere_get_installed_effects. - Avoid destructive baking. Keep changes parameterized and reversible.
- Do not use legacy effect-enable or named grain, glow, vignette, drop-shadow, stroke, and cinematic-bar helpers in this verified workflow; they either lack portable component-state readback or can return instructions/requested values instead of a verified mutation. Use the generic verified effect path.
- Do not claim visual quality from parameter success alone; request a frame review when appearance matters.
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.
- 12d ago First seen · 29 lines · 56 tokens per session scan A 409d3805cb0c
premiere-look-effects is a skill published in the GitHub repository ayushozha/AdobePremiereProMCP (99 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 498 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.