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 commands/spillwavesolutions/image_gen/image-gengit clone --depth 1 https://github.com/SpillwaveSolutions/image_genWhat 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 | $0.00018 | $0.00242 |
| Opus 5 | $0.00009 | $0.00121 |
| Sonnet 5 | $0.00004 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
image-gen 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
Run skills/image-gen/scripts/generate.py.
- Choose kind: cover (Nano Banana Pro, 16:9) or article (Nano Banana 2).
- Write a specific prompt. Covers are metaphorical. In-article images explain one concept.
- Call generate.py with
--outputunderwork/images/. - Use
--engine-hint imagen|grok|codexwhen the host matters.grokmaps to the scriptablegrok-imgCLI, which needsgrok-img auth loginorXAI_API_KEY. Codex must write the requested PNG; prose-only results fail closed with a retained prompt sidecar. - If exit 2, no backend is on PATH. The prompt sidecar is already written. Run
/image-gen-install, installgrok-img, or use Codex. - Integrate the PNG with 50–125 character ALT text.
Do not invent a PNG. Do not send Mermaid or PlantUML through this command.
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 · 18 lines · 18 tokens per session scan A 45264fddb233
image-gen is a command published in the GitHub repository SpillwaveSolutions/image_gen (2 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 242 once invoked, about $0.0001 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.
Other commands, from other repositories
write-sdd
Write DESIGNDOC.md using the arc42 SDD template, Mermaid-first diagrams, one voice pack.
write-architecture
Write a C4-first architecture document with Mermaid flowcharts and sequences.
write-wireframe
Draw PlantUML Salt UI wireframes for every user-facing screen. Render PNG or SVG.
write-design-doc
Alias for write-sdd. Emits DESIGNDOC.md.
work-update
Send work summary to configured Matrix room.
grade-config
Grade CLAUDE.md and AGENTS.md files against best practices.