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 agentmods add skills/motion-creative/motion-creative-plugin/qa-feedbacknpx skills add Motion-Creative/motion-creative-plugin --skill qa-feedbackgit clone --depth 1 https://github.com/Motion-Creative/motion-creative-pluginWhat 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 | $0.00081 | $0.02552 |
| Opus 5 | $0.00041 | $0.01276 |
| Sonnet 5 | $0.00016 | $0.00510 |
| Haiku 4.5 | $0.00008 | $0.00255 |
Grade A, and why
qa-feedback 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 2d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative QA & Feedback
Review a creative asset across 6 dimensions: brand alignment, hook quality, strategic positioning, concept integrity, production quality, and brief adherence. Every piece of feedback connects to data, brand guidelines, or the strategic framework.
Phase 1: Get the Asset
1a. Parse Arguments
- Asset (
$ARGUMENTS): The creative to review. Can be:- A URL to the ad
- A screenshot description
- A creative entity ID from Motion
- A description of the asset
--type: video, image, static, carousel, or unknown. Default: unknown (infer from context).--brief: The original brief this asset was built from. Optional but enables brief adherence check.
If no asset is provided, ask the user what they want reviewed.
1b. Load Context
- Read
${CLAUDE_PLUGIN_ROOT}/motion-creative.config.mdfor brand voice, creative do's/don'ts, target audience. If the file does not exist, use these defaults and suggest the user run/customize:default_date_preset: LAST_30_DAYS- Brand guidelines: pull from
get_workspace_brand
- Read
${CLAUDE_SKILL_DIR}/../creative-strategist/SKILL.mdfor methodology. - Use
default_date_presetfrom settings as the datePreset for all calls unless the user specified a date range. - Read
${CLAUDE_SKILL_DIR}/../creative-strategist/references/concept-standards.mdfor quality bar. - Read
${CLAUDE_SKILL_DIR}/../creative-strategist/references/insight-quality.mdfor insight quality standards. - Read
${CLAUDE_SKILL_DIR}/../creative-strategist/references/evaluation-framework.mdfor the 4-Question Evaluation Framework, metric pattern correlations, Ready/Iterate/Rethink call, and multi-persona feedback methodology.
Phase 2: Pull Comparison Data
The SPEND call must come first (it returns goalMetric and spendThreshold). Then dispatch remaining calls in parallel.
get_auth_context()— resolve workspaceget_creative_insights(workspaceId, insightType="SPEND", datePreset="LAST_30_DAYS", limit=5, withAggregatedInsights=true)— spend leaders + account-level aggregates
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.
- 2d ago First seen · 227 lines · 81 tokens per session scan A 1791dbdb865a
qa-feedback is a skill published in the GitHub repository Motion-Creative/motion-creative-plugin (20 stars, last pushed 3mo ago), licensed MIT. It adds 81 tokens to every session and 2,552 once invoked, about $0.0004 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
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
flier
Design a print-ready, single-page flier as one self-contained HTML file: exactly one fixed-size page.
ideate
Generate image-based alternatives, remixes, or new design directions from a Product Design brief. Use when the user asks for design variants, visual exploration, remixes, or image-generated approaches from provided context.
ip-as-logo
Generate extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition. Use when creating an animal, creature, robot, ghost, plant, object, or other character image, including when the agent…
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
ppt-design
使用 HTML 设计与生成高质量演讲幻灯片（PPT/Deck）。当用户希望生成、设计、修改幻灯片、deck、slides、presentation、汇报、提案、pitch、课件时触发。主干：1280×720px 可编辑 HTML 幻灯片 + 唯一 editable HTML→EditableSlideScene→OOXML 管线 + 数据/信息可视化意识 + 5 种设计哲学 + 反 AI slop + 单页自包含 slide-XX.html。不生图；缺图用可编辑原语或占位并标注建议补图。.