Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leiming2333/Vision-Toolkitnpx agentmods add skills/leiming2333/vision-toolkit/text-to-imageWrote 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/leiming2333/vision-toolkit/text-to-image)<a href="https://agentmods.dev/skills/leiming2333/vision-toolkit/text-to-image"><img src="https://agentmods.dev/badge/skills/leiming2333/vision-toolkit/text-to-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/leiming2333/vision-toolkit/text-to-image"><img src="https://agentmods.dev/badge/skills/leiming2333/vision-toolkit/text-to-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 | $0.00049 | $0.01657 |
| Opus 5.5 | $0.00020 | $0.00663 |
| Sonnet 5.5 | $0.00010 | $0.00331 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
text-to-image 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 2mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text to Image
Generate an image from a natural-language prompt by calling the standalone generate_image.py script in this project. This skill is available to any agent and does not require the MCP server to be running — it calls the providers directly.
Relationship with the MCP generate_image tool
This project exposes image generation through two entry points that share the same providers/ code and the same environment-variable configuration (API keys / endpoints / models):
- MCP
generate_imagetool (preferred) — available when the MCP server is connected. Use it first. - This Skill (fallback) — a standalone script. Use it when:
- the MCP server is not connected / not running,
- the MCP
generate_imagetool call fails or times out, - or you are in a context where only a Skill works (CI, batch, an agent without MCP).
Configuration source: the Skill reads the same environment variables as the MCP server (OPENAI_API_KEY / DASHSCOPE_API_KEY / GEMINI_API_KEY and the corresponding *_BASE_URL / *_IMAGE_MODEL). By default the Skill shares the MCP config — whatever the MCP server uses, the Skill uses too.
Skill-independent config (optional): the Skill also supports a separate config layer via SKILL_*-prefixed env vars. At runtime the Skill reads SKILL_<name> first; if unset it falls back to <name>. The MCP server does not read SKILL_* vars, so MCP behavior is unaffected. Set SKILL_* vars only when you want the Skill to use a different key / endpoint / model than MCP — e.g. SKILL_OPENAI_API_KEY, SKILL_OPENAI_BASE_URL, SKILL_DASHSCOPE_API_KEY, SKILL_GEMINI_API_KEY. If neither SKILL_* nor the shared key is set, tell the user to set the relevant environment variable.
The Skill script also has built-in provider auto-fallback: if the chosen provider fails, it automatically retries the other configured providers. So prefer the MCP tool first; if it fails, run this Skill script and it will try every available provider.
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.
- 2mo ago First seen · 117 lines · 49 tokens per session scan A 3a749e18df78
text-to-image is a skill published in the GitHub repository leiming2333/Vision-Toolkit (0 stars, last pushed 25d ago), licensed MIT. It adds 49 tokens to every session and 1,657 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 2026-08-31.
text-to-image compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| text-to-imageleiming2333/Vision-Toolkit | Skill | 0 | 25d ago | MIT | A | 49 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |