Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add titusz/skills/plugin install imagegenWrote 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/titusz/skills/generate-image)<a href="https://agentmods.dev/skills/titusz/skills/generate-image"><img src="https://agentmods.dev/badge/skills/titusz/skills/generate-image/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/titusz/skills/generate-image"><img src="https://agentmods.dev/badge/skills/titusz/skills/generate-image.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 | $0.00157 | $0.01835 |
| Opus 5.5 | $0.00063 | $0.00734 |
| Sonnet 5.5 | $0.00031 | $0.00367 |
| Haiku 4.5 | $0.00016 | $0.00184 |
Grade B, and why
generate-image scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`[features] image_generation = true` in `~/.codex/config.toml` (flag off). How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Image
Turn a request into one or more raster images via Codex's built-in image_gen tool,
driven by the bundled script. The script owns every gotcha (stdin piping, API-key
stripping, read-only sandbox, harvesting by thread id), so never call codex exec
directly, never write API scripts, and never ask for an OPENAI_API_KEY.
Tooling
uv run "${CLAUDE_PLUGIN_ROOT}/scripts/codex_image.py" <command> ...
Abbreviated as codex_image.py below. If ${CLAUDE_PLUGIN_ROOT} is unset, resolve the
path relative to this file (../../scripts/codex_image.py).
Commands:
| Command | Purpose |
|---|---|
doctor |
Verify codex on PATH, ChatGPT auth, image_generation flag, no API keys |
generate |
Run one generation/edit; prints JSON with outputs, sidecar, errors |
fit |
Resize/convert an existing image (--fit WxH, --fit-mode, -o) |
generate options: --prompt-file (preferred) or --prompt, --name <slug>,
--edit <img> (repeatable, edit target), --ref <img> (repeatable, subject/composition
reference), --style <card.md>, --count N, --fit WxH, --fit-mode cover|contain,
--format png|jpeg|webp, --out <dir> (default cauldron/images), --timeout,
--keep-log. At most 5 images total across --edit, --ref, and the style's refs.
Output layout
cauldron/
├── images/<slug>/
│ ├── prompt.md # the spec you wrote for the latest run
│ ├── <slug>-1.png # numbered, never overwritten (re-runs append -2, -3 …)
│ └── <slug>.json # sidecar: every run's spec, refs, style text, thread id, outputs
└── styles/<name>.md # art-style cards (see the art-style skill)
The script creates folders as needed. cauldron/ is scratch space: if the project's
.gitignore does not cover it, say so once and let the user decide.
Workflow
What ships with it
1 file 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.
- 1mo ago First seen · 143 lines · 157 tokens per session scan B 7b876607b0b7
generate-image is a skill published in the GitHub repository titusz/skills (2 stars, last pushed 14d ago), licensed MIT. It adds 157 tokens to every session and 1,835 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.