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 glifxyz/glif-mcp-server --skill make-imagesgit clone --depth 1 https://github.com/glifxyz/glif-mcp-serverWrote 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/glifxyz/glif-mcp-server/make-images)<a href="https://agentmods.dev/skills/glifxyz/glif-mcp-server/make-images"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/make-images/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/glifxyz/glif-mcp-server/make-images"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/make-images.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 | $0.00202 | $0.00923 |
| Opus 5.5 | $0.00081 | $0.00369 |
| Sonnet 5.5 | $0.00040 | $0.00185 |
| Haiku 4.5 | $0.00020 | $0.00092 |
Grade A, and why
make-images scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL "<media url>" -o drafts/posters/01-noir.png How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make the images the user described and put them where they can find them. The user's explicit instructions come first, within host safety rules.
1. Write the brief
Say what each image shows, not which model to use. Include:
- Subject and scene: what is in the picture and what it is doing.
- Style: a named look (pixel art, watercolor, 1990s desktop screenshot), a palette, lighting and mood. Name a reference style, not a living artist.
- Size: aspect ratio and pixel size, such as 16:9 at 1920×1080 or 1:1 at 1024×1024.
- Count: how many images, and what varies between them.
- Text in the image: the exact words in quotes, kept short. Say "no text" otherwise.
- References: upload a logo, sketch or style sample with
upload_file, only after the user agrees to send that file to Glif. With shell access, passfilename(andkindif unclear), then run the returnedcommandwith the real path. Pass the returnedfileUrlinattachments. Say what to keep from it: "Use the attached mark exactly, don't redraw it."
A series goes in one brief. Number the items and give each a short name and what makes it different, so Glif can title the outputs to match.
Use real people's faces only with their consent. Don't make images that pass as real photos of real people or events.
2. Check cost, then run once
Generation spends the user's Glif credits. A direct request ("make an image of…") is approval. If the images were your own idea, list them in a line each and wait for a yes.
Call compose_project once with the whole brief. Share the projectUrl. Follow the run with get_job_status, passing the jobId as job_id. A series can take minutes, so keep working meanwhile. A pending status or timeout is not a reason to start another run, and never retry a failure on your own.
3. Save and check
Download every result. In a codebase, use a folder the build does not ship, with a subfolder per series. Check the ignore and build config first, and never use public/ or static/. Elsewhere, use the folder the user named or the current directory.
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.
- 7d ago First seen · 49 lines · 202 tokens per session scan A 804540368711
make-images is a skill published in the GitHub repository glifxyz/glif-mcp-server (215 stars, last pushed 7d ago), licensed MIT. It adds 202 tokens to every session and 923 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other skills, from other repositories
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-workflow-patterns
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, batch processing, or scheduled…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…
n8n-code-tool
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…