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 mgiovani/cc-arsenal --skill codex-imagegengit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/codex-imagegen)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/codex-imagegen"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/codex-imagegen/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/mgiovani/cc-arsenal/codex-imagegen"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/codex-imagegen.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 | $0.00136 | $0.02302 |
| Opus 5.5 | $0.00054 | $0.00921 |
| Sonnet 5.5 | $0.00027 | $0.00460 |
| Haiku 4.5 | $0.00014 | $0.00230 |
Grade A, and why
codex-imagegen 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 22d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Imagegen: Illustrated Asset Generation via Codex CLI
Generate polished, professionally-illustrated raster art (mascots, hero images, logos, sprite sheets, product mockups) by driving Codex CLI's $imagegen skill. Use this instead of hand-drawing shapes in SVG/CSS/SwiftUI when the asset needs to look designed, not programmatically constructed.
Scope check (do this first)
This skill wraps a multi-minute, credit-billed Codex run and is the default handler for image-generation requests:
- Architecture/flow/sequence diagram → tell the user to use
docs-diagraminstead and stop here. - Otherwise, continue: the cost gate in Phase 2 decides whether to confirm before running.
Ground rules
- Single-quote the whole prompt.
$imagegenmust reachcodexliterally, not be shell-expanded: a double-quoted or unquoted prompt containing$imagegenbreaks. - Never fabricate a model ID.
gpt-6-sol(agent) and GPT Image 2.5 Sunburst (gpt-image-2.5-sunburst, images) are this recipe's known-good defaults at time of writing; ifcodexrejects one, checkcodex --version/codex exec --helpfor a current one rather than guessing a replacement. - Name the image model in the prompt. Codex has no image-model flag (
-msets the agent model), so every prompt opens with$imagegen using gpt-image-2.5-sunburst via the built-in image tool. Codex can't report which image model the backend actually ran, so don't claim more than "requested Sunburst". - Never claim chroma removal or file output succeeded without viewing the pixels.
sips hasAlpha: yesproves nothing; open the PNG. - Stop before an expensive run and confirm when the brief is a batch (multiple assets), a consistency-critical asset (recurring character/mascot), or explicitly says "final"/"official": this is real spend and multi-minute wall-clock time, not a free retry.
Phase 1: Environment check
codex --version
- Not found → tell the user to install Codex CLI (
npm i -g @openai/codexorbrew install codex, thencodex login) and stop. codex execrejects the model or auth → see references/troubleshooting.md.- Run from the target repo's root so codex's relative move-file paths land in the right workspace.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago Changed · -5 lines 8674e90e80e6
- 1mo ago Changed 26f6d547deca
- 1mo ago Changed · +2 lines · -3 tokens per session fd79d91ade72
- 1mo ago Changed · +1 lines 2bba10cf7a03
- 1mo ago First seen · 154 lines · 139 tokens per session scan A c41ab908bef0
codex-imagegen is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 2d ago), licensed MIT. It adds 136 tokens to every session and 2,302 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
basic-skill
Summarize small CSV files and identify the highest revenue month.
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or…
handoff-protocols
Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or…
parallel-investigation
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist…
hypothesis-testing
Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or…
trace-and-isolate
Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component…