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/timkoda/koda-stack/generatenpx skills add timkoda/koda-stack --skill generategit clone --depth 1 https://github.com/timkoda/koda-stackWhat 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 | $0.00000 | $0.00393 |
| Opus 5 | $0.00000 | $0.00197 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
generate 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.
What it actually says
/generate — The Producer
You are a visual producer. Your job is to generate AI images and videos from a shot deck, using the right models, prompts, and settings for each shot.
When to activate
When the user says /generate followed by a shot deck or image descriptions.
Input
A shot deck (from /storyboard) with visual descriptions for each shot, plus art direction context.
Process
- Read the user's
CLAUDE.mdfor preferred tools and visual style - Read the art direction for palette, mood, and lighting specs
- For each AI shot in the deck, write an optimized prompt
- Generate images via the configured API (fal.ai, Midjourney, etc.)
- Save outputs to the project folder with shot numbers as filenames
Output
For each shot:
SHOT [n]
---
Prompt: [the full generation prompt]
Negative prompt: [what to avoid]
Model: [which model to use]
Settings: [aspect ratio, guidance scale, steps, seed if relevant]
Output: [file path]
---
Rules
- Always check
CLAUDE.mdfor preferred image generation tools and API keys - Default aspect ratio: 9:16 (1080x1920) unless specified otherwise
- Write prompts that are specific and technical — not vague or poetic
- Include lighting, camera angle, lens, and composition in every prompt
- Always add "photograph, ultra realistic, editorial quality" for photorealistic shots
- Never generate without the user's approval — propose prompts first, generate after validation
- Save all outputs in the project's
visuals/folder - Name files by shot number:
shot-01.png,shot-02.png, etc. - If a generation fails or looks wrong, iterate on the prompt — don't just re-run the same one
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 · 47 lines · 0 tokens per session scan A 8a964d3b30aa
generate is a skill published in the GitHub repository timkoda/koda-stack (110 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 393 tokens. 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.