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 vladkesler/initrunner --skill prompt-craftgit clone --depth 1 https://github.com/vladkesler/initrunnerWrote 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/vladkesler/initrunner/prompt-craft)<a href="https://agentmods.dev/skills/vladkesler/initrunner/prompt-craft"><img src="https://agentmods.dev/badge/skills/vladkesler/initrunner/prompt-craft/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/vladkesler/initrunner/prompt-craft"><img src="https://agentmods.dev/badge/skills/vladkesler/initrunner/prompt-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00814 |
| Opus 5 | $0.00015 | $0.00407 |
| Sonnet 5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
prompt-craft 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image prompt crafting skill.
When to activate
Use this skill when you need to construct a prompt for generate_image from a user's description. Always activate this before calling generate_image.
Methodology
1. Extract intent
Parse the user's description for:
- Subject: what is in the image (person, object, scene, abstract)
- Style: art style (photorealistic, illustration, watercolor, etc.)
- Mood: emotional tone (calm, energetic, mysterious, professional)
- Colors: specific colors or palette preferences
- Composition: framing, perspective, layout
- Context: where will this image be used (logo, social media, presentation, personal)
If any of these are missing and matter for the result, ask the user.
2. Check memory
Recall style preferences and brand guidelines:
recall("style_preference")
recall("brand_guideline")
Apply any saved preferences unless the user's current request explicitly overrides them.
3. Build the prompt
Construct the prompt using this structure:
[Subject description], [style], [composition], [lighting], [mood], [details]
Rules for effective prompts:
- Be specific about the subject: "a golden retriever puppy sitting on a red cushion" not "a dog"
- Name the art style explicitly: "digital illustration", "oil painting style", "35mm film photography", "vector art"
- Specify lighting: "soft natural light", "dramatic side lighting", "neon glow", "golden hour"
- Include composition cues: "close-up", "wide angle", "bird's eye view", "centered", "rule of thirds"
- Add atmosphere: "moody", "minimalist", "vibrant", "muted tones"
- Keep prompts under 400 characters for best results
- Avoid negations ("no background") -- describe what you want, not what you do not want
4. Select parameters
Choose the right parameters for the use case:
| Use case | Size | Style | Quality |
|---|---|---|---|
| Social media post | 1024x1024 | vivid | standard |
| Blog header | 1792x1024 | natural | hd |
| Phone wallpaper | 1024x1792 | vivid | hd |
| Logo / icon | 1024x1024 | natural | hd |
| Quick concept | 1024x1024 | natural | standard |
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.
- 9d ago First seen · 109 lines · 30 tokens per session scan A a978b7d46da7
prompt-craft is a skill published in the GitHub repository vladkesler/initrunner (41 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 814 once invoked, about $0.0002 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
video-prompt-engineer
Write and fix prompts for AI video generation.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
prism
Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.
happyhorse-prompt-studio
Interactive prompt studio for HappyHorse 1.0 video generation. Guides users through scenario discovery with vivid examples, then assembles production-ready prompts in JP/CN/EN. Use when someone wants to create AI video content with HappyHorse but doesn't know where to start, or when they have a specific scenario and…
prompt-cache-agent-harness
Plan and inspect prompt-cache behavior for long-running Claude agent loops. Use when a user wants to split stable tool, system, and history context into cacheable layers, compare captured cache metadata, estimate cost impact from supplied pricing inputs, or keep durable memory outside the cached prefix.
image-generation
Enhances image generation prompts with Subject-Context-Style structure, style anchors, character consistency, mcp-image workflows. Not for video generation, TTS, FFmpeg, audio, or design-to-code.