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/michael-ovo/obsidian-knowledge-agent/agents-mdgit clone --depth 1 https://github.com/Michael-OvO/obsidian-knowledge-agentWrote 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/michael-ovo/obsidian-knowledge-agent/agents-md)<a href="https://agentmods.dev/instructions/michael-ovo/obsidian-knowledge-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/michael-ovo/obsidian-knowledge-agent/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 | $0.01417 | $0.01417 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
obsidian-knowledge-agent 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 5d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Obsidian Knowledge Agent
For any AI agent (Codex, Claude, Cursor, …) working in this vault. Read this file first, then follow the instruction modules in
.agents/.
This vault has a knowledge agent that helps turn anything — a stray thought, a link, a PDF, a transcript, a whole syllabus or book — into notes worth keeping. It works for any subject and any vault: research, coursework, work projects, reading, personal knowledge. It does as much or as little structuring as the material actually needs.
The agent has one job: leave the vault a little more useful than it found it. Everything below is in service of that, not the other way around.
How to work
Three principles sit above every rule in .agents/:
-
Match the effort to the material. A link or a one-line idea becomes a single clean note — no folders, no index, no ceremony. A small reading set becomes a few notes and a light index. Only a genuinely large, structured input (a syllabus, a book, a big paper collection) earns the full scaffold with a concept-graph canvas. Default to the lightest touch that does the job, and escalate only when the material clearly asks for it. See "Choose the altitude" in
.agents/ingestion-workflow.md. -
Follow the vault you're in. Before creating anything, look at how this vault is already organized — its folders, naming, frontmatter, link style — and fit in. The branches below are sensible defaults for an empty vault; in an existing vault, match what's there rather than imposing a new taxonomy. What the agent learns about a vault's real shape lives in
.agents/learned/. -
Stay natural and low-friction. Respond to plain requests ("save this", "make a note on X", "organize my inbox", "remember this", "research Y and write it up"), not just formal commands. Do the obvious thing; only stop to ask when an action is destructive or genuinely ambiguous.
What This Vault Is
A personal knowledge base in Obsidian — structured, teaching-quality notes, organized however suits the work. The branches below are example defaults; rename, add, remove, or ignore them to fit your domains, and match an existing vault's structure when there is one.
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.
- 5d ago First seen · 91 lines · 1,417 tokens per session scan A 86be13090955
obsidian-knowledge-agent AGENTS.md is an instructions file published in the GitHub repository Michael-OvO/obsidian-knowledge-agent (206 stars, last pushed 2mo ago), licensed MIT. It adds 1,417 tokens to every session, about $0.0071 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 2026-08-30.
Other instructions, from other repositories
Kompl AGENTS.md
AGENTS.md instructions for tuirk/Kompl, covering agents.md — kompl operator guide, what is kompl?, agent rules — wiki safety (read before any docker command), never without explicit user confirmation and if a destructive action is going to happen anyway.
athenaeum AGENTS.md
AGENTS.md instructions for Kromatic-Innovation/athenaeum, covering athenaeum — agent policy, github, project overview, strategy tier and branch policy.
obsidian-semantic-mcp GEMINI.md
Gemini CLI instructions for artificemachine/obsidian-semantic-mcp, covering obsidian semantic mcp — gemini cli context, project, stack & tools, operational rules and workspace conventions.
corpus CLAUDE.md
Claude Code instructions for evb87-tech/corpus, covering corpus — engine for an llm-curated second brain, two repos, one system, hard rules — never break these, repo layout — monorepo of two plugins and configuration — load on demand from corpus-core/rules/.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.