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 agentmods add skills/vinsonconsulting/limner/dallenpx skills add vinsonconsulting/limner --skill dallegit 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/dalle)<a href="https://agentmods.dev/skills/vinsonconsulting/limner/dalle"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/dalle.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00938 |
| Opus 5 | $0.00028 | $0.00469 |
| Sonnet 5 | $0.00011 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
dalle 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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DALL·E prompt builder
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Limner's DALL·E pipeline calls OpenAI's Images API on the gpt-image-1 family. It follows detailed instructions well, so the prompt carries most of the weight while the knobs handle format and background. This skill is the procedure; the recipe at the end lists the knobs and their values.
Procedure
- Write a descriptive prompt: name the subject, composition, lighting, and style in plain language. gpt-image-1 rewards specificity.
- Choose size and quality for the use: square for icons, portrait or landscape for scenes; higher quality trades latency and cost for detail.
- For a logo or UI mark that must drop onto any surface, request a transparent background and a format that keeps alpha.
- To render text in the image, quote the exact words and where they go, keep the text short, and verify spelling in the result.
- To restyle an existing image rather than start over, pass it as a source image URL; the edit preserves the subject while applying the prompt.
Knob reference
The recipe below is generated from the Limner guidance core (@limner/core),
the same source the MCP dalle-builder 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.
DALL·E prompt recipe
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Limner’s DALL·E pipeline calls OpenAI’s Images API, defaulting to the gpt-image-1 model. Write a descriptive prompt: gpt-image-1 follows detailed instructions closely and renders legible text in the image far better than earlier models. Then set the knobs below. Note that OpenAI’s 2025/2026 consolidation retired DALL·E 2/3 and removed the legacy style and response_format parameters; Limner does not send them.
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.
- 5d ago First seen · 69 lines · 56 tokens per session scan A b99c14a95326
dalle is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 24d ago), licensed Apache-2.0. It adds 56 tokens to every session and 938 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-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).
flux-3-prompt-doctor
Use when diagnosing a FLUX 3 brief before generation. Resolve missing, conflicting, or schema-changing requirements.