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 ShaftHQ/SHAFT_ENGINE --skill design-skillsgit clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINEWrote 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/shafthq/shaft_engine/design-skills)<a href="https://agentmods.dev/skills/shafthq/shaft_engine/design-skills"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/design-skills/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/shafthq/shaft_engine/design-skills"><img src="https://agentmods.dev/badge/skills/shafthq/shaft_engine/design-skills.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 | $0.00032 | $0.01014 |
| Opus 5.5 | $0.00013 | $0.00406 |
| Sonnet 5.5 | $0.00006 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
design-skills 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 today.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design skills (add-on)
Optional ChaosEngine add-on. Installed at .chaos-engine/addons/design-skills/
only when a user passed --with-design-skills. Without it, use core
ui-delivery for UI work.
Iron rules
- Load one card for the current step, never the whole set. Return here for the next step.
- Web work loads core ui-delivery first. Cards add design judgment; they never replace red-then-green tests or the viewport x theme matrix.
- Every deliverable ends with its card's Verify list run through
design_qc.py.
skippedis notpass: install the tool or report the gap. - Real evidence only: real captures, real command output, real product facts. Mockups are labelled. No generated text inside images.
- Licences first: record every font, track, voice, model, and footage source in the asset manifest before using it.
- Deliver after QC and an independent review pass; earlier files are DRAFT.
- A design document (brief, storyboard, visual direction) runs the core design loop when the owner asks for review.
Cards
| Step | Card | Use when |
|---|---|---|
| Plan | D01 brief and storyboard | any video, ad, or visual campaign starts |
| Story | D21 explainer arc | an explainer needs hook, arc, audience versions |
| Launch | D22 launch video | short showcase, poster, share copy |
| Brand | D02 brand system | tokens, logo, voice are needed |
| Web | D03 visual direction | a surface needs an aesthetic idea |
| Landing | Public landing | product landing page for humans, search, and agents |
| Web | D04 interface audit | a UI needs a rule-by-rule audit |
| Type | D05 typography and layout | scale, measure, grid |
| Color | D06 color and contrast | palettes, contrast, overlays |
| Image | D07 image graphics | posters, OG cards, thumbnails, diagrams |
| Motion | D08 motion principles | easing, timing, holds, flashes |
| Motion | D09 HTML motion graphics | lower thirds, kinetic type |
| Motion | D10 technical animation | architecture or data flow |
| Capture | D11 screen capture | real terminal or browser footage |
| Edit | D12 edit assembly | EDL-driven ffmpeg edit |
| Cut | D13 cutting and pacing | rhythm, dead air, J/L cuts |
| Color | D14 color grading | BT.709 conform and grade |
| Audio | D15 mix and loudness | ducking, two-pass loudnorm |
| Audio | D16 noise removal | noisy speech |
| Voice | D17 voice-over (TTS) | narration without a recording |
| Access | D18 captions | SRT/WebVTT, burned-in captions |
| Clean | D19 restoration and upscaling | denoise, upscale |
| Ship | D20 delivery QC | final encode, manifest, gate |
What ships with it
27 files 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.
- addon.json 466 B
- INVENTORY.md 3.9 KB
- references/audio-mix-loudness.md 3.1 KB
- references/brand-system.md 2.5 KB
- references/captions-subtitles.md 2.4 KB
- references/color-contrast.md 2.0 KB
- references/color-grading.md 2.6 KB
- references/cutting-pacing.md 3.6 KB
- references/delivery-qc.md 5.5 KB
- references/design-brief-storyboard.md 2.9 KB
- references/edit-assembly.md 3.0 KB
- references/explainer-arc.md 2.8 KB
- references/html-motion-graphics.md 4.7 KB
- references/image-graphics.md 2.3 KB
- references/launch-video.md 3.2 KB
- references/motion-principles.md 2.4 KB
- references/noise-removal.md 2.2 KB
- references/pipelines/runbook.md 6.4 KB
- references/pipelines/technical-video.md 2.6 KB
- references/screen-capture.md 3.2 KB
- references/technical-animation.md 2.0 KB
- references/typography-layout.md 3.0 KB
- references/video-restoration-upscaling.md 2.0 KB
- references/voice-over-tts.md 3.3 KB
- references/web-interface-audit.md 2.1 KB
- references/web-visual-direction.md 2.1 KB
- scripts/design_qc.py 72 KB runs code
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.
- today Changed · +1 lines bbdd6f86700b
- 7d ago Changed · +1 lines 359415982b9b
- 8d ago Changed · +1 lines 32385c835f3b
- 12d ago Changed · +3 lines f6dafb43c322
- 13d ago First seen · 58 lines · 32 tokens per session scan A dcf6ade18518
design-skills is a skill published in the GitHub repository ShaftHQ/SHAFT_ENGINE (414 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,014 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
form-patterns
A reference guide for arranging managed forms in the 1C platform. It describes common layouts, naming conventions, events, properties, and advanced patterns for different form types.
img-grid
An image overlay that draws numbered vertical and horizontal lines over a PNG or JPG image.
audit-accessibility
Ensure the plugin's custom UI components are accessible to users with screen readers and other assistive technologies.
interface-edit
An editor for the command interface of a 1C subsystem, the part that controls which commands users see and where they appear.
eddi-screens
How an EDDI Manager page is actually built — the app shell, the list-page pattern, detail pages, the config-editor chrome, wizards, and loading/empty/error states. Load before creating or restructuring a page.
eddi-ui
EDDI Manager's UI vocabulary — the existing primitives and shared components, their variant props, the brand tokens, and the styling rules. Load before writing or editing any component that renders.