A rulebook for an Obsidian wiki, a linked collection of Markdown notes. It defines page types, metadata fields, tags, links, indexes, source boundaries, and task-writing rules.

It is used before importing, searching, saving, checking, or indexing knowledge in the wiki.

It gives every wiki operation the same format and prevents the wiki from changing source folders that are meant to remain read-only.

wiki-schema — Skill for Claude Code by ihudak/ihudak-claude-plugins

Install

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.

Any agent

npx skills add ihudak/ihudak-claude-plugins --skill wiki-schema

Clone the repo

git clone --depth 1 https://github.com/ihudak/ihudak-claude-plugins

Made for: Claude Code.

Or install obsidian-llm-wiki, the plugin that ships this one along with the rest of its 11 skills, 10 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ihudak/ihudak-claude-plugins/wiki-schema/github.svg)](https://agentmods.dev/skills/ihudak/ihudak-claude-plugins/wiki-schema)

Your own site

<a href="https://agentmods.dev/skills/ihudak/ihudak-claude-plugins/wiki-schema"><img src="https://agentmods.dev/badge/skills/ihudak/ihudak-claude-plugins/wiki-schema/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ihudak/ihudak-claude-plugins/wiki-schema"><img src="https://agentmods.dev/badge/skills/ihudak/ihudak-claude-plugins/wiki-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,354 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00098	$0.03354
Opus 5.5	$0.00039	$0.01342
Sonnet 5.5	$0.00020	$0.00671
Haiku 4.5	$0.00010	$0.00335

Measured 1mo ago against content hash c7bd4687b5c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wiki-schema 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 1mo 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.

plugins/obsidian-llm-wiki/skills/wiki-schema/SKILL.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki Schema — obsidian-llm-wiki

Vault knowledge schema for the wiki layer. All wiki skills read this file before operating. This is the single source of truth for conventions, boundaries, and formats.

All /wiki-* slash commands follow these conventions identically across both Claude Code and GitHub Copilot.

Critical Boundary Rule

Wiki operations (ingest, scan, query, save, lint, hot, tags-refresh) MUST NEVER write to or delete files from:

Meetings/
Daily/
Projects/
Customers/
People/
Clippings/
Research/

These are Layer 1 — read-only knowledge sources. The wiki reads them; it never modifies them.

The wiki layer includes two task-management commands (/wiki-task and /wiki-tasks-extract) that intentionally write outside the wiki directory — to Projects/ and Tasks.md. These commands follow the task-creation rules in _shared/task-rules.md. Two more write outside it to fixed files only: /wiki-tags-refresh updates .obsidian/copilot/tag-index.md, and /wiki-init writes .obsidian/copilot/ and the wiki blocks in the vault's CLAUDE.md and .github/copilot-instructions.md. All other wiki operations write only to wiki/, and to .raw/ only to archive what they ingested or, in /wiki-scan, to write an HTML file's markdown conversion beside it.

Three-Layer Source Model

Layer 1 — Sources (read-only for wiki):
  Meetings/            ← meeting notes (primary knowledge source)
  Daily/               ← daily notes — extract ## Notes and ## Worklog sections only;
                          skip Dataview task queries (they are not content)
  Projects/            ← project context, decisions, tech stack
                          includes Products/, Data Generators/, Jira/ subdirs
  Customers/           ← customer notes
  People/              ← person/team notes
  Clippings/           ← web clippings
  Research/            ← research notes

Layer 2 — Inbox (read + archive after processing):
  .raw/                ← external sources: PDFs, exports, web clips
                          The ONLY directory wiki may clean up.
                          After successful ingest: move to .raw/_processed/YYYY-MM/
                          For HTML files: use defuddle if available before ingesting
                            npx defuddle parse <file> --md

Layer 3 — Wiki output (every wiki page is written here):
  wiki/      ← all wiki pages and meta files

Read the full file on GitHub · 427 lines

Changes

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.

1mo ago Changed · +5 lines c7bd4687b5c5
2mo ago First seen · 422 lines · 98 tokens per session scan A c47c2679e1dd

Subscribe to this mod's changes

wiki-schema is a skill published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 3,354 once invoked, about $0.0004 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 2026-09-05.

Claude Code Memory and context Writing and docs ai-agents ai-code-review claude-code-plugins developer-productivity documentation-automation

wiki-schema next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wiki-schemaihudak/ihudak-claude-plugins	Skill	2	1mo ago	MIT	A	98	Claude Code
ctx-upgrademksglu/context-mode	Skill	34k	yesterday	none	A	12	Claude Code
cdb-scanAvijit07x/claude-db	Skill	233	15d ago	Apache-2.0	A	72	Claude Code, Codex
handoffAvijit07x/claude-db	Skill	233	15d ago	Apache-2.0	A	87	Claude Code, Codex
catchupAvijit07x/claude-db	Skill	233	15d ago	Apache-2.0	B	71	Claude Code, Codex
session-recapsxhmilyoyo/sundayhao-plugins	Skill	9	yesterday	Apache-2.0	A	39	Claude Code
permanent-memory-loadernguyenthienthanh/aura-frog	Skill	25	15d ago	MIT	A	48	Claude Code