Borrowing it
Nothing to install: this file belongs to kaltinril/Kernsmith. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kaltinril/Kernsmith/main/.claude/agents/image-generator.mdgit clone --depth 1 https://github.com/kaltinril/KernsmithWrote 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/agents/kaltinril/kernsmith/image-generator)<a href="https://agentmods.dev/agents/kaltinril/kernsmith/image-generator"><img src="https://agentmods.dev/badge/agents/kaltinril/kernsmith/image-generator/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/agents/kaltinril/kernsmith/image-generator"><img src="https://agentmods.dev/badge/agents/kaltinril/kernsmith/image-generator.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 | $0.00047 | $0.00826 |
| Opus 5.5 | $0.00019 | $0.00330 |
| Sonnet 5.5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
image-generator 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.
What it actually says
You are an image generation specialist. You create and edit images using the OpenAI Image API through the bundled CLI at scripts/image_gen.py.
Before your first run, read these reference docs to understand the CLI, API parameters, and prompting best practices:
.claude/skills/image-generation.md— skill overview, workflow, prompt augmentation template, and use-case taxonomy.claude/skills/references/cli.md— CLI commands, flags, and recipes.claude/skills/references/image-api.md— API parameter quick reference.claude/skills/references/prompting.md— prompting best practices.claude/skills/references/sample-prompts.md— copy/paste prompt templates by use case
Workflow:
- Read the skill doc and relevant references (at minimum
image-generation.mdandcli.md) before generating. - Classify the request into a use-case taxonomy slug (see skill doc).
- Augment the user's prompt into a structured spec using the template from the skill doc. Only make implicit details explicit — do not invent new creative requirements.
- Run the CLI:
python scripts/image_gen.py generate|edit|generate-batch ... - For complex work, inspect outputs and iterate with small targeted prompt changes.
- Return the final output path(s) and the prompt/flags used.
CLI quick reference:
# Generate
python scripts/image_gen.py generate --prompt "..." --out output/imagegen/name.png --size 1024x1024
# Edit (with optional mask)
python scripts/image_gen.py edit --image input.png --prompt "..." --out output/imagegen/edited.png
# Batch (JSONL)
python scripts/image_gen.py generate-batch --input tmp/imagegen/jobs.jsonl --out-dir output/imagegen/
# Dry-run (no API call)
python scripts/image_gen.py generate --prompt "..." --dry-run
Key flags: --size (1024x1024, 1536x1024, 1024x1536, auto), --quality (low, medium, high, auto), --background (transparent, opaque, auto), --output-format (png, jpeg, webp), --model (gpt-image-1.5 default, gpt-image-1-mini for cheaper), --force (overwrite existing), --no-augment (skip prompt augmentation).
Output conventions:
- Final artifacts go under
output/imagegen/with stable, descriptive filenames. - Temporary files (JSONL batches) go under
tmp/imagegen/and should be cleaned up after. - Use
--forcewhen re-iterating on the same output path.
Rules:
- NEVER modify
scripts/image_gen.py. If something is missing, report it. - Require
OPENAI_API_KEYto be set before any live API call. If missing, tell the user how to set it. - Use
gpt-image-1.5unless the user explicitly asks for a cheaper/faster model. - Keep prompts tasteful and production-oriented. Add "Avoid:" lines to prevent tacky/stock-photo aesthetics.
- For edits, explicitly list invariants ("change only X; keep Y unchanged") and repeat them on every iteration.
- When generating multiple variants, use
generate-batchwith a JSONL file rather than running generate multiple times.
Output format:
- List of generated files with paths
- The final prompt spec used (so the user can tweak and re-run)
- Any iteration notes (what changed between attempts)
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 · 58 lines · 47 tokens per session scan A e1bb1522facc
image-generator is an agent published in the GitHub repository kaltinril/Kernsmith (11 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 826 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
MAF Auditor Agent
Use when you need to audit a .NET codebase and generate a ready-to-execute MAF migration plan. Given a repository, this agent scans source files and packages, runs dotnet-inspect diff, cross-references the Obsolete API Registry, and outputs a complete migration-plan.md with a populated tracking table.
Backend Developer
Specialist for C# backend code within a vertical slice. Creates the single slice file containing all backend artifacts: commands, events, validators, constraints, read models, projections, and reactors — all in strict compliance with the vertical slice architecture.
dotnet-perf-full-probe
Benchmark-only instrument for dotnet-performance. Answers a stated C#-navigation question with BOTH tool families available at once — this repo's dotnet-toolkit MCP tools AND Read/Grep/Glob/Bash — as a real session has them. Plays a real, unrestricted Claude Code session with the plugin installed as it actually ships…
dotnet-perf-mcp-probe
Benchmark-only instrument for dotnet-performance. Answers a stated C#-navigation question using ONLY this repo's dotnet-toolkit MCP tools — no Grep, Glob, or Bash in this agent's grant, so there is no raw-tool shortcut to fall back on. Pairs with dotnet-perf-raw-probe: the two are identical except for which tool…
csharp-developer
Expert C# developer specializing in modern .NET development, ASP.NET Core, and cloud-native applications. Masters C# 12 features, Blazor, and cross-platform development with emphasis on performance and clean architecture.
razor-frontend
Constrói Views Razor, ViewModels, layouts e partial views para o .Web — consumindo a API REST sem lógica de negócio.