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/pbeens/obsidian-agents.md/agents-mdgit clone --depth 1 https://github.com/pbeens/obsidian-agents.mdWrote 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/pbeens/obsidian-agents.md/agents-md)<a href="https://agentmods.dev/instructions/pbeens/obsidian-agents.md/agents-md"><img src="https://agentmods.dev/badge/instructions/pbeens/obsidian-agents.md/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 | $0.02148 | $0.02148 |
| Opus 5 | $0.01074 | $0.01074 |
| Sonnet 5 | $0.00430 | $0.00430 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
obsidian-agents.md 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
[!TIP] If
AGENTS2.mdexists in the root, read it for additional local maintenance and privacy rules.
Purpose
This vault is a personal Obsidian knowledge base. Agents should turn incoming material into clean, linked notes, with canonical People pages, canonical Project pages, and usable task views.
Scope
- Work only within this vault unless explicitly told otherwise.
- Preserve the existing vault structure where possible.
- Do not bulk-migrate, rename, or rewrite legacy notes without approval.
- Prefer minimal, reviewable changes that solve the current request.
Expected Deliverables
- Canonical
people/notes for people entities. - Canonical
projects/notes for project entities. - Clean notes promoted from
_raw/. - Task overviews built with Obsidian Tasks, Bases, or simple Markdown lists.
- Reusable local skills and shared scripts when a workflow repeats.
Folder Map
README.md: root entrypoint and navigation.AGENTS.md: durable agent rules and folder map.tasks.md: active work, blockers, and handoff notes._raw/: staging inbox for clipped or rough material.people/: canonical people pages.projects/: canonical project pages.skills/: reusable vault-specific workflows.scripts/: shared utilities and validation helpers.- Existing folders like
Topic Pages/,Bases/,Daily Notes/, andClippings/remain valid parts of the vault.
Daily Note Convention
- A daily note means a note whose filename is only a date, typically
YYYY-MM-DD.md. - Treat notes with a date plus extra words in the filename as ordinary notes, not daily notes.
- When the user asks to process a folder or all files in a folder, do not assume daily notes are included unless the user explicitly says so.
- When the user says "daily note", target the date-only note for that day.
- If a workflow needs a daily note destination, use the date-only file for the relevant day rather than creating a titled note.
Working Rules
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 · 136 lines · 2,148 tokens per session scan A cabcf430cd32
obsidian-agents.md AGENTS.md is an instructions file published in the GitHub repository pbeens/obsidian-agents.md (20 stars, last pushed 4mo ago), licensed MIT. It adds 2,148 tokens to every session, about $0.0107 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
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).