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 fmind/dot --skill documentation-sitegit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/documentation-site)<a href="https://agentmods.dev/skills/fmind/dot/documentation-site"><img src="https://agentmods.dev/badge/skills/fmind/dot/documentation-site/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/fmind/dot/documentation-site"><img src="https://agentmods.dev/badge/skills/fmind/dot/documentation-site.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 | $0.00025 | $0.01553 |
| Opus 5.5 | $0.00010 | $0.00621 |
| Sonnet 5.5 | $0.00005 | $0.00311 |
| Haiku 4.5 | $0.00003 | $0.00155 |
Grade A, and why
documentation-site 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Sites
Use Zensical as the default static site generator for project documentation, courses, and blogs; keep an existing generator only when the project depends on it or the user asks. course-development owns learning design and executable labs; repository-docs owns README and AGENTS consistency.
Workflow
- Inspect the project: keep existing content, URLs, and publication rules. For an MkDocs or Hugo site, follow migration instead of scaffolding over it.
- Bootstrap with a locked dependency: check the latest release, then add it as a dev dependency so
uv runanduv sync --lockedinclude it. Skipuv initin an existing Python project; runzensical newin a scratch directory whendocs/orzensical.tomlalready exists, because it never overwrites files.uv init --bare <slug> && cd <slug> uv add --dev zensical uv run zensical new . - Apply the starter: replace the generated files with the zensical.toml, index.md as
docs/index.md, extra.css asdocs/stylesheets/extra.css, and abbreviations.md asincludes/abbreviations.md; deletedocs/markdown.md. Fill every<placeholder>, set the realsite_urlwith its hosting prefix, and drop unused sections. The starter enables instant navigation, Copy as Markdown,llms.txt, social cards, a glossary, checked snippets, and minified HTML; configuration explains each feature and the optional ones (blog, tags, redirects, API reference, versions, offline). - Write under
docs/: one H1 per page, explicitnav, a sectionindex.mdfor overviews, relative.mdlinks, and adescriptionin front matter for search and social cards. Use authoring for page types and syntax, and the lesson template for courses. - Wire tasks and ignores: merge mise.toml into the task graph and add
site/and.cache/to.gitignore. Use dprint for Markdown and python-stack for executable examples. - Validate:
uv run --locked zensical build --clean --strictmust printNo issues foundand exit 0. Preview withuv run --locked zensical serve(defaultlocalhost:8000) and check navigation, search, both palettes, a 390 px viewport, keyboard use, and code copy; use playwright for screenshots. Run lesson code and external links separately. - Publish: replace the generated
.github/workflows/docs.ymlwith the pinned docs.yml, which builds every pull request strictly and deploysmainto GitHub Pages; github-actions owns pins and audits. Enabling Pages or deploying needs publication authority.
What ships with it
10 files 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.
- 2d ago Changed 2cb044f7d9e4
- 5d ago Changed 50b63cfe2c72
- 8d ago Changed ba9311affb93
- 10d ago Changed 3c59e76bc351
- 11d ago Changed · -10 lines · +5 tokens per session f23b2178acd4
- 13d ago Changed 84327df95916
- 19d ago Changed 5959f943e838
- 25d ago Changed 7045839f3490
- 29d ago First seen · 59 lines · 20 tokens per session scan A 8818e3bfc09b
documentation-site is a skill published in the GitHub repository fmind/dot (11 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,553 once invoked, about $0.0001 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 2026-09-17.
Other skills, from other repositories
course-development
Design executable technical curricula, lessons, and labs with prerequisites, guided practice, accessibility, platform checks, and course release acceptance.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.