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 vinsonconsulting/limner --skill pipeline-routergit clone --depth 1 https://github.com/vinsonconsulting/limnerWrote 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/vinsonconsulting/limner/pipeline-router)<a href="https://agentmods.dev/skills/vinsonconsulting/limner/pipeline-router"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/pipeline-router/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/vinsonconsulting/limner/pipeline-router"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/pipeline-router.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 | $0.00055 | $0.01197 |
| Opus 5 | $0.00028 | $0.00598 |
| Sonnet 5 | $0.00011 | $0.00239 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
pipeline-router 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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline router
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Use this skill to pick the right generation pipeline before you generate, so you do not pay for a raster you then have to trace or composite text by hand. It routes by what the asset is first, then by cost and speed. The reference at the end is the decision table.
Procedure
- Name the output kind. Is it vector or raster? Does it need readable text in the image? Does it need a transparent background? These decide the pipeline before cost does.
- Match the requirement to a pipeline. Vector and logo work go to Recraft; in-image text goes to DALL·E; painterly, art-directed imagery goes to Midjourney when the user can run it. Use the reference table for the full mapping.
- Weigh cost and speed to break ties. Midjourney carries no Limner API charge but the user runs it and brings the result back; DALL·E and Recraft bill per call and return directly. Prefer compose over paying for another generation.
- Hand off to the chosen pipeline. Load its skill (midjourney, dalle, or recraft) and build the prompt there.
- Plan the finish. If the asset needs print scale, upscale it; if a raster mark needs to scale, vectorize it; otherwise convert and resize in compose.
Judgment
- Decide the output kind before the budget. The wrong format costs more to fix later than the right pipeline costs up front.
- Reach for Recraft vector from the start when the asset must scale, rather than generating a raster and tracing it afterward.
- Prefer Midjourney when the user has a subscription and wants art direction; prefer DALL·E or Recraft when you need the asset returned in one step.
- When two pipelines both fit, choose the one whose native output needs the least post-processing.
Routing reference
The table below is generated from the Limner guidance core (@limner/core), the
same source the MCP pipeline-router prompt serves, so this skill and that prompt
cannot drift. Do not edit the generated region by hand; run
pnpm --filter @limner/limner-agent gen:skills instead.
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.
- 8d ago First seen · 83 lines · 55 tokens per session scan A 0d62b24b8c07
pipeline-router is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 27d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,197 once invoked, about $0.0003 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 skills, from other repositories
universal-video-prompt-skill
Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across providers, or when the target model is not yet available and the work must proceed on another one.
model-aware-image-prompt-engineer
Model-aware image prompt engineering for any agent or image generation workflow. Use when writing, improving, translating, debugging, or evaluating prompts for OpenAI image models, Gemini Nano Banana, Midjourney, FLUX, Qwen-Image, Z-Image, Stable Diffusion, SDXL, Pony, Illustrious, NoobAI, Animagine, HunyuanImage…
image-prompt
Use when the user wants to turn a short idea into a rich, production-grade image-generation prompt — posters, landing-page or UI mockups, ads, editorial layouts, photoreal scenes, game screenshots, logos, or illustrations. Builds ONE structured, copy-paste-ready prompt optimized for gpt-image-2 by default, following…
atlas-cloud
Atlas Cloud API integration skill — quickly call 300+ AI image generation, video generation, audio (TTS, music, speech-to-text), 3D generation, and LLM models through a unified API. Use this skill when the user needs to integrate AI image generation (e.g., Flux, Seedream, DALL-E), AI video generation (e.g., Kling…
ideogram-prompt
Prompting technique guide for Ideogram image generation via the connected Ideogram MCP (generateimage, describeimage, remiximage, editimage). Use whenever the user wants to generate, remix, or edit an image with Ideogram — including moodboards, style-matching a reference image, extracting a visual "recipe" from…
nano-banana-image-skill
Model-aware image prompting for Nano Banana Pro and Nano Banana 2. Covers generation, editing, continuity, text-in-image, style routing, and structured JSON output.