Borrowing it
Nothing to install: this file belongs to pvliesdonk/markdown-vault-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pvliesdonk/markdown-vault-mcp/main/.agents/skills/writing-documentation/SKILL.mdgit clone --depth 1 https://github.com/pvliesdonk/markdown-vault-mcpWrote 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/pvliesdonk/markdown-vault-mcp/writing-documentation)<a href="https://agentmods.dev/skills/pvliesdonk/markdown-vault-mcp/writing-documentation"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/writing-documentation/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/pvliesdonk/markdown-vault-mcp/writing-documentation"><img src="https://agentmods.dev/badge/skills/pvliesdonk/markdown-vault-mcp/writing-documentation.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 | $0.00061 | $0.01045 |
| Opus 5.5 | $0.00024 | $0.00418 |
| Sonnet 5.5 | $0.00012 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
writing-documentation 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 18d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing documentation
docs/contribute/docs-structure.md is the contract: the ownership rule, the places documentation may go, one topic per page, and the security-model link. This skill is the order in which you apply it. When the two appear to disagree, the page wins; don't restate it here.
1. Domain or non-domain?
Decide what the knowledge is before deciding where it goes. The test: would it be true of any server generated from the template? Then it's non-domain, and it belongs to the template. Don't write it in this project, not even as a short copy. File it on the template (the authoring-issues-prs skill routes it) and link to the template page if one exists.
If you can't decide, say so in the change or the issue with both readings. Don't guess silently.
2. Does a page for this topic already exist?
Search docs/ and README.md for the topic before writing. If a page answers the question, change that page. A second page on the same topic is the most common way documentation starts contradicting itself.
3. Which place?
For domain knowledge, use the table in the contract page:
- adding to a non-domain topic (a mount, an environment file, a client config for this server): the
DOMAIN-*block on the template page for that topic; - a fact the code already holds (a config field, a default, a tool's parameters or what it returns): its source, so the generator carries it. Never hand-edit a
GENERATED-*region or a generated page underdocs/reference/; after changing a tool, resource, prompt or CLI option, runuv run python scripts/gen_reference.py; - a worked example for one tool or prompt: its
DOMAIN-EXAMPLE-<name>slot on the generated page; - a how-to or explanation of this server's own features: a page in
docs/use/; - API reference for a library the project ships:
docs/reference/api/; - release narrative:
docs/releases/; - internal design:
docs/design/.
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.
- 18d ago First seen · 58 lines · 61 tokens per session scan A 878daf5c7efa
writing-documentation is a skill published in the GitHub repository pvliesdonk/markdown-vault-mcp (35 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,045 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 2026-10-05.
Other skills, from other repositories
docs-rag
Use when a project's markdown docs, specs, ADRs or decision logs need to be searchable by meaning from the agent, when a searchnotes tool (docs-rag-mcp) is connected, when its results carry labels like [semantic 0.71], [both], [exact match] or [superseded → ...], when it answers "No relevant results", or when a…
mnemonic
Search local indexed markdown knowledge bases. Use when the user asks to find notes, dig up a concept from personal docs, cross-reference ideas across wikis, or answer from indexed local files. Triggers on "look up in notes", "search my docs", "what did I write about", "find in my vault", "check my index", "retrieve…
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
siyuan-plugin-development
Official frontend plugin development workflow. After the user explicitly opts in, clarify missing requirements, confirm a short plan, implement in a managed copy, verify, and package. Installation and activation require separate authorization.
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.