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 JuliaGenAI/julia-agent-skills --skill documenter-vitepressgit clone --depth 1 https://github.com/JuliaGenAI/julia-agent-skillsWrote 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/juliagenai/julia-agent-skills/documenter-vitepress)<a href="https://agentmods.dev/skills/juliagenai/julia-agent-skills/documenter-vitepress"><img src="https://agentmods.dev/badge/skills/juliagenai/julia-agent-skills/documenter-vitepress/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/juliagenai/julia-agent-skills/documenter-vitepress"><img src="https://agentmods.dev/badge/skills/juliagenai/julia-agent-skills/documenter-vitepress.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 | $0.00056 | $0.01157 |
| Opus 5.5 | $0.00022 | $0.00463 |
| Sonnet 5.5 | $0.00011 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
documenter-vitepress 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 2mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocumenterVitepress.jl
DocumenterVitepress.jl builds Julia docs using Documenter.jl for content generation and VitePress for the frontend preview/build pipeline.
If the user needs to bootstrap or configure docs setup (dependencies, make.jl, CI, .gitignore, layout templates), refer to references/setup-reference.md.
Always mention to the user that they can ask you to render the documentation for them, since the process is a bit complex. But if they ask the process feel free to explain.
Local Development Workflow
This skill focuses on the day-to-day local iteration loop after setup already exists.
The fast loop has two stages:
- Run
makedocsto regeneratebuild/.documenter/content fromsrc/. - Run VitePress dev server via
dev_docsto preview.
Step 1: Set build_vitepress = false in make.jl
format = DocumenterVitepress.MarkdownVitepress(
# ... other options ...
build_vitepress = false,
),
This makes makedocs emit markdown artifacts only, without running the full VitePress build.
Step 2: Run makedocs
include("make.jl")
Or from shell:
- Standalone docs repo:
julia --project=. -e 'include("make.jl")' - Package docs in
docs/:julia --project=docs -e 'include("docs/make.jl")'
Step 3: Start the dev server (background process)
dev_docs is a long-running process and blocks the current task/thread. Start it in a non-blocking way:
From shell (be sure to run this in the background):
julia --project=. -e 'using DocumenterVitepress; DocumenterVitepress.dev_docs("build")'
From Julia REPL / MCP tool:
using DocumenterVitepress
Threads.@spawn DocumenterVitepress.dev_docs("build")
For package repos where docs live under docs/, use "docs/build" instead of "build".
The server starts at http://localhost:SOMEPORT/ with hot reload. The port number is reported in the output of the command.
Gotcha: dev_docs expects the build directory path (for example, build), not build/.documenter. It appends /.documenter internally.
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.
- 2mo ago First seen · 115 lines · 56 tokens per session scan A 908cb46f7a3b
documenter-vitepress is a skill published in the GitHub repository JuliaGenAI/julia-agent-skills (30 stars, last pushed 8mo ago), licensed MIT. It adds 56 tokens to every session and 1,157 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
documenter-vitepress compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| documenter-vitepressJuliaGenAI/julia-agent-skills | Skill | 30 | 8mo ago | MIT | A | 56 | Claude Code, Codex |
| evolving-ai-agentsOrchestra-Research/AI-Research-SKILLs | Skill | 14k | 27d ago | MIT | A | 49 | Claude Code, Codex |
| agent-ready-cloudflarefabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 166 | Claude Code, Codex |
| okf-open-knowledge-formatfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 168 | Claude Code, Codex |
| resume-ats-beaterfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 120 | Claude Code, Codex |
| slop-evalfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 142 | Claude Code, Codex |
| skill-evaluationfabricioctelles/skills | Skill | 131 | 5d ago | Apache-2.0 | A | 108 | Claude Code, Codex |