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/external-toolsnpx skills add vinsonconsulting/limner --skill external-toolsgit clone --depth 1 https://github.com/vinsonconsulting/limnerWhat 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 | $0.00062 | $0.00931 |
| Opus 5 | $0.00031 | $0.00465 |
| Sonnet 5 | $0.00012 | $0.00186 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
external-tools 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External editors & handoff
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Limner generates and composes assets, then hands off to a desktop editor when a task needs manual work it does not perform itself. Use this skill to route a finished or in-progress asset to the right editor and export it in the format that editor reads best.
When to hand off
Hand off once Limner has taken the asset as far as generation and composition can. Typical triggers:
- Pixel-level retouching, masking, or compositing a generated raster.
- Authoring or cleaning up vector paths beyond what Recraft emits.
- Multi-page or CMYK print layout and prepress.
- Hand-painting or natural-media work on top of a generation.
Procedure
- Name the job. Decide which of the needs above the task fits; that points to the editor more reliably than preference does.
- Pick the target from the reference table below: match the job to the editor's "Best for" entry, and confirm it reads the format you plan to export.
- Export from Limner in that editor's preferred input format. Match the container to the work: SVG for vector editors, a layered PSD or TIFF for raster compositing, PDF for print prep. The file-types skill covers the trade-offs.
- Hand the exported asset to the user with the editor named, so they can open and continue it locally. Limner does not drive the desktop editor itself.
Editor reference
The table below is generated from the Limner guidance core (@limner/core), the
same source the MCP limner://reference/external-tools resource serves, so this
skill and that resource cannot drift. Do not edit the generated region by
hand; run pnpm --filter @limner/limner-agent gen:skills instead.
External editors & handoff targets
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
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.
- 2d ago First seen · 67 lines · 62 tokens per session scan A f8c5f0c9f48b
external-tools is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 21d ago), licensed Apache-2.0. It adds 62 tokens to every session and 931 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-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.
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.