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 illuminated-manuscriptgit 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/illuminated-manuscript)<a href="https://agentmods.dev/skills/vinsonconsulting/limner/illuminated-manuscript"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/illuminated-manuscript/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/illuminated-manuscript"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/illuminated-manuscript.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 | $0.00050 | $0.01034 |
| Opus 5 | $0.00025 | $0.00517 |
| Sonnet 5 | $0.00010 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
illuminated-manuscript 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Illuminated manuscript
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
This is the flagship workflow. It proves the research-to-generation loop rather than a single generation: you research a tradition, generate each decorative element, compose them into one page, render the text, and deliver a single asset. The reference at the end names the elements and which pipeline makes each.
Procedure
- Research first. Use your web tools to pin down the tradition the user wants: period, region, script, palette, and the motif vocabulary (borders, initials, marginalia). Summarize what you find; it steers every prompt.
- Generate the miniature. Use the Midjourney or DALL·E skill to produce the central illustration in the researched style. This is the anchor image.
- Generate the initial and decoration. Use the Recraft skill for vector borders and the historiated initial; request transparent backgrounds so they composite cleanly. To keep a motif consistent across elements, pass an earlier generation back in as image input.
- Compose the page. Use the compose tool to place the miniature, initial, and border into one layout, then renderText to set the body in a period- appropriate font. Hold the researched palette fixed so the parts read as one work.
- Deliver one page. Return the composed image through its capability URL so the user receives a single fetchable asset, not a pile of layers.
- Hand off if asked. For manual gilding or print prep, point the user to a desktop editor through the external-tools skill.
Judgment
- Stop researching once you can name the script, the palette, and three or four signature motifs. More research past that rarely changes the prompts.
- Generate the anchor miniature before the decoration so the border and initial can echo its palette.
- Prefer vector output for borders and initials; it scales and composites without halos around the edges.
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.
- 9d ago First seen · 81 lines · 50 tokens per session scan A 6e70cdc397fd
illuminated-manuscript is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 28d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,034 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
flux-3-product-ads
Use when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped audio, floating products, off-model plates, and reports that claim a pass the build did not give.
bfl-api
BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.
flux-3-archival-formats
Use when a FLUX 3 video needs a period or archival look. Covers naming a recording format instead of a mood, per-format artifacts, and templates.
flux-3-prompt-doctor
Use when diagnosing a FLUX 3 brief before generation. Resolve missing, conflicting, or schema-changing requirements.
flux-image-best-practices
Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.
flux-3-keyframes-continuation
Use when a FLUX 3 video must be built from supplied images or video. Covers keyframes (i2v) and continuation (v2v).