What is image_gen CLAUDE.md?

Repository instructions for a multi-host plugin that generates article cover images and illustrations for tools such as Claude Code, Codex, and Cursor.

Installing an image backend, generating cover or article images, selecting a specific image engine, and running the plugin’s unit tests.

They specify the available commands, fallback order, model choices, required PNG files, and behavior when no image backend is available.

image_gen CLAUDE.md — Instructions file by SpillwaveSolutions

Install

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.

agentmods

npx agentmods add instructions/spillwavesolutions/image_gen/claude-md

Clone the repo

git clone --depth 1 https://github.com/SpillwaveSolutions/image_gen

Per session 395 This file is loaded in full into every session.

When invoked 395 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00395	$0.00395
Opus 5	$0.00198	$0.00198
Sonnet 5	$0.00079	$0.00079
Haiku 4.5	$0.00040	$0.00040

Measured 2d ago against content hash d1b7c7e61bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

image_gen CLAUDE.md 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.

CLAUDE.md · 50 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code when working in this repository.

What this is

A multi-host plugin (Claude Code, Codex, Grok Build, Cursor, Agent Plugins 1.0) that generates article cover images and in-article illustrations.

Commands

python3 skills/image-gen/scripts/install_imagen.py
python3 skills/image-gen/scripts/generate.py --kind cover --output work/images/cover.png --prompt "PROMPT"
python3 -m unittest discover -s tests -v

Backend auto

imagen on PATH. Policy imagen-cli-vars.
Then grok-img. Policy grok-imagine.
Then Codex agent. Policy grok-imagine.
Else write <stem>_imagen.prompt.txt and exit 2.

Use --engine-hint imagen|grok|codex to select a runner. grok maps to grok-img. Codex is an agent-host adapter, not an imaginary image generate subcommand. Both must write the requested PNG for a run to pass.

Models

Pin Nano Banana 2 as the CLI default. --kind cover selects Nano Banana Pro (gemini-3-pro-image).

Layout

skills/image-gen/     skill + scripts + references
commands/             /image-gen, /image-gen-install
plugin.json           Agent Plugins v1
.claude-plugin/       Claude Code
.codex-plugin/        Codex
.grok-plugin/         Grok Build
.cursor-plugin/       Cursor

WikiTicket SDD (worklog)

Track work with WikiTicket SDD. Never hand-edit .work/*.jsonl.

Changes

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 · 50 lines · 395 tokens per session scan A d1b7c7e61bea

Subscribe to this mod's changes

image_gen CLAUDE.md is an instructions file published in the GitHub repository SpillwaveSolutions/image_gen (2 stars, last pushed 5d ago), licensed MIT. It adds 395 tokens to every session, about $0.0020 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.

agentic-skill claude-code-skill

document-specialist-skill AGENTS.md

AGENTS.md instructions for SpillwaveSolutions/document-specialist-skill: When the user asks for a design document, SDD, architecture document, or DESIGNDOC.md, load SKILL.md then references/workflows/design-workflow.md.

SpillwaveSolutions/document-specialist-skill · 102 tokens

document-specialist-skill CLAUDE.md

Claude Code instructions for SpillwaveSolutions/document-specialist-skill: See AGENTS.md and SKILL.md. Intent DESIGN writes DESIGNDOC.md from references/templates/markdown/DESIGNDOC.md.

SpillwaveSolutions/document-specialist-skill · 37 tokens

matrix-skill AGENTS.md

AGENTS.md instructions for netresearch/matrix-skill, covering matrix skill, index of scoped agents.md, repo structure, commands — matrix-communication and read / edit / react / redact.

netresearch/matrix-skill · 2,738 tokens

matrix-skill CLAUDE.md

Claude Code instructions for netresearch/matrix-skill, a project described as: Three Agentic Skills for Matrix: encrypted chat with a daemon that follows rooms live, Synapse homeserver administration, and content guidance for announcements. Chat works with any homeserver; administration requires Synapse.

netresearch/matrix-skill · 3 tokens

matrix-skill GEMINI.md

Gemini CLI instructions for netresearch/matrix-skill, a project described as: Three Agentic Skills for Matrix: encrypted chat with a daemon that follows rooms live, Synapse homeserver administration, and content guidance for announcements. Chat works with any homeserver; administration requires Synapse.