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/jmet04/ai-apprentice/packaging-design-apprenticenpx skills add JMET04/ai-apprentice --skill packaging-design-apprenticegit clone --depth 1 https://github.com/JMET04/ai-apprenticeWhat 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 | $0.00050 | $0.01297 |
| Opus 5 | $0.00025 | $0.00648 |
| Sonnet 5 | $0.00010 | $0.00259 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
packaging-design-apprentice 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Packaging Design Apprentice
Use this skill for packaging design work. The workflow is deliberately staged; never skip directly from a request or Image2 sample to final delivery or CAD.
Teacher Communication
Use the bundled warm-human-communication skill throughout this workflow. During clarification, say what is already understood and ask only the smallest missing data group that blocks safe design. During failure, name the failed stage, preserve any intact sample or mask, and give the smallest recovery step. During correction, acknowledge the exact region or engineering boundary that was misread and apply it without changelog or customer-service language. Keep manufacturing risks and review gates explicit even when the tone is warm.
Required Sequence
- Clarify requirements. Ask for the product type, packaging/box type, confirmed internal or product dimensions (
L x W x Hplus unit), material/thickness, weight and transport needs, closure, printing/finish, references, and required output formats. Ask only the smallest useful set of questions at once. Never invent a missing consequential dimension. - Form a deep implementation plan and compile the first prompt. Select a packaging template, identify all dimension sources and assumptions, and define structural constraints and manufacturing risks. Then invoke the bundled
image2-prompt-optimizer;record-planautomatically writesimage2-initial-prompt-guidance.json. Show a public structured trace, not private chain-of-thought. - Generate one Image2 sample from the guidance packet. Read and follow the compiled prompt packet before calling the Image2/image generation tool. Preserve the packet and original image. The sample is not deliverable and its pixels are not dimension truth. Never generate while
readyForGeneration=false. - Self-check before teacher review. Check all eight items in
transparent_ai_apprentice_packaging_sample_self_check_v1: dimension completeness, unit consistency, panel/shape topology, cut/crease/slot conflicts, closure clearances, manufacturing feasibility, annotation legibility, and confirmation that Image2 pixels were not used as dimensions. Record failures honestly. - Open the Chinese mask workbench. Use
create-transparent-sketch-overlay-kit.mjs --backdrop <sample image>and show the self-check issues beside the sample. Wait for the teacher to submit marks or text. Do not infer approval from opening or closing the mask. - Apply Image2 local editing. Send the original sample, submitted mask, teacher text, and self-check issues to Image2 as a local edit. Preserve before/after evidence. Do not regenerate unrelated regions.
- Hand off to AICAD. Only after the local edit exists, run
packaging-design-workflow.mjs --action prepare-cad-handoff. Use the integratedaicad-agentplugin to create the parametric plan and CAD outputs. Confirmed teacher/engineering dimensions outrank standards, mask semantics, and Image2 appearance in that order. Never measure CAD dimensions from Image2 pixels. - Final teacher review. Show CAD outputs, native annotations, preview, validation report, error root causes, and any new prevention rules. Keep the decision review-only; do not claim technology acceptance or production readiness.
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 · 69 lines · 50 tokens per session scan A 023a6edcc312
packaging-design-apprentice is a skill published in the GitHub repository JMET04/ai-apprentice (1 stars, last pushed 13d ago), licensed MIT. It adds 50 tokens to every session and 1,297 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…