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 IvanLutsenko/awac-ai-agent-plugins --skill prompt-craftinggit clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-pluginsWrote 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/ivanlutsenko/awac-ai-agent-plugins/prompt-crafting)<a href="https://agentmods.dev/skills/ivanlutsenko/awac-ai-agent-plugins/prompt-crafting"><img src="https://agentmods.dev/badge/skills/ivanlutsenko/awac-ai-agent-plugins/prompt-crafting/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/ivanlutsenko/awac-ai-agent-plugins/prompt-crafting"><img src="https://agentmods.dev/badge/skills/ivanlutsenko/awac-ai-agent-plugins/prompt-crafting.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 | $0.00072 | $0.01410 |
| Opus 5.5 | $0.00029 | $0.00564 |
| Sonnet 5.5 | $0.00014 | $0.00282 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
prompt-crafting 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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt-crafting for image generators
Each target has different sweet spots. Pick the section that matches target, then expand the brief.
Universal pre-step — interpret the brief by context
Before tuning per-target, decide style from context, not from a fixed preset:
- If the brief implies a person or scene (e.g. "женщина у окна на закате") → photoreal cinematic.
- If the brief is conceptual / abstract ("одиночество в большом городе") → editorial illustration or minimal poster.
- If the brief mentions a known medium ("в стиле акварели", "пиксель-арт", "лого") → respect it.
- If unclear → photoreal, neutral lighting, 3/4 angle, 50mm. Default for ambiguous briefs.
Always include: subject, environment, lighting, composition, mood, technical params (camera/render hints, aspect ratio). Exclude: identifiable real people unless the brief explicitly names one — say "person resembling X" only if the brief insists.
If translate_to_english is enabled in settings, the final prompt MUST be English regardless of brief language.
Gemini (Imagen 3) — target=gemini
URL: https://gemini.google.com/app
Format: flowing natural-language paragraph. ~480 token soft limit. Single paragraph or two short ones — no bullets, no comma-tag style.
Strengths: photorealism, environments, product shots, lighting nuance. Weak spots: stylized illustration is hit-or-miss; on-image text often broken.
Negatives: inline ("no text in the image", "no extra fingers"). Imagen has no formal negative prompt.
Aspect ratio: mention it in prose ("widescreen 16:9", "vertical portrait 3:4"). Imagen accepts limited ratios via the UI; the prompt itself is the hint.
Template:
A [subject doing X] in [environment]. [Lighting and time of day]. [Composition: framing, angle, depth of field]. [Mood and atmosphere]. Shot on [camera/lens hint] for photorealism, ultra-detailed, [aspect ratio]. No text, no logos.
Example brief: "уставший разработчик ночью у компьютера"
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.
- 1mo ago First seen · 108 lines · 72 tokens per session scan A 5db69dd6695b
prompt-crafting is a skill published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (3 stars, last pushed 5d ago), licensed MIT. It adds 72 tokens to every session and 1,410 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…