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 instructions/bezata/kobsidian/agents-mdgit clone --depth 1 https://github.com/bezata/kObsidianWrote 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/instructions/bezata/kobsidian/agents-md)<a href="https://agentmods.dev/instructions/bezata/kobsidian/agents-md"><img src="https://agentmods.dev/badge/instructions/bezata/kobsidian/agents-md.svg" alt="Measured on agentmods" 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 | $0.00821 | $0.00821 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
kObsidian AGENTS.md 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kObsidian Development Guidelines
Runtime
- Bun + strict TypeScript ESM is the only supported runtime.
- MCP is implemented with
@modelcontextprotocol/sdkv1.x,McpServer, stdio, and Streamable HTTP. - Zod v4 schemas define public tool contracts.
Project Structure
src/config/ environment parsing and runtime settings
src/domain/ note, link, tag, task, Dataview, Mermaid, Marp, Kanban, canvas, workspace logic
src/lib/ shared filesystem, markdown, REST client, error, and result helpers
src/schema/ reusable Zod primitives and models
src/server/ MCP server factory, transports, and tool registration
tests/ Vitest fixture and integration tests
docs/ generated tool inventory and supporting docs
Commands
bun install
bun run dev:stdio
bun run dev:http
bun run typecheck
bun run test
bun run lint
bun run build
bun run inventory
Code Style
- Keep domain logic transport-agnostic.
- Prefer filesystem-first behavior where possible.
- Return typed JSON objects through
structuredContent. - Keep source-preserving Markdown edits region-based.
- Do not commit secrets,
.envfiles,node_modules, or build output.
Working in the wiki
kObsidian ships a wiki.* namespace that layers the "LLM Wiki" pattern on top
of the low-level primitives. The schema is documented inside each vault as
wiki/wiki-schema.md once wiki.init has run.
wiki.init— scaffoldwiki/{Sources,Concepts,Entities}/plusindex.md,log.md,wiki-schema.md(idempotent).wiki.ingest— file a source: createswiki/Sources/<slug>.mdwith canonical frontmatter and an append-only log entry. Returns aproposedEditsarray (index line, concept-stub creations, entity-citation inserts) for the caller to apply vianotes.create/notes.edit— never applies cross-reference edits directly.wiki.logAppend— typed log entry, format## [YYYY-MM-DD] <op> | <title>sogrep '^## \[' log.md | tail -5just works.wiki.indexRebuild— regenerateindex.mdgrouped by category.wiki.query— rank wiki pages for a topic (filename / alias / tag / summary / body hits). LLM drills into results withnotes.read.wiki.lint— read-only health check: orphans, broken links, stale sources, missing concept/entity pages, tag singletons, index parity.wiki.summaryMerge— add a cited section to a concept or entity page (creates the page with canonical frontmatter if absent); bumpsupdated.
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.
- 4d ago First seen · 81 lines · 821 tokens per session scan A 117b008a555d
kObsidian AGENTS.md is an instructions file published in the GitHub repository bezata/kObsidian (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 821 tokens to every session, about $0.0041 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 instructions, from other repositories
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
pi-llm-wiki AGENTS.md
AGENTS.md instructions for zosmaai/pi-llm-wiki, covering agents.md, project, tech stack, file layout and conventions.
obsidian-llm-wiki CLAUDE.md
Claude Code instructions for green-dalii/obsidian-llm-wiki, a project described as: Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
llm-brain CLAUDE.md
Instructions for kimsanguine/llm-brain, covering llm-brain — claude code 운영 지침, 가드레일 (절대 위반 금지), 프라이버시 경계 (agent memory os), 명령어 and ingest.
obsidian-llm-wiki CLAUDE.md
Instructions for levi-qiao/obsidian-llm-wiki, covering llm wiki - 核心架构, 一句话总结, 语言与角色, 三层架构 and 1. raw 层(内容不可变,位置可变).
cmds-llm-wiki AGENTS.md
Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.