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/ar9av/obsidian-wiki/copilot-instructionsgit clone --depth 1 https://github.com/Ar9av/obsidian-wikiWhat 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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
obsidian-wiki copilot-instructions.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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Wiki — Copilot Context
This project is a skill-based framework for building and maintaining an Obsidian knowledge base using AI coding agents. There are no scripts or dependencies — everything is markdown instructions that the agent executes directly.
Project Overview
- Purpose: Build and maintain an Obsidian wiki using the LLM Wiki pattern (Andrej Karpathy).
- Tech Stack: Markdown only. No code, no dependencies. The AI agent IS the runtime.
- Key Config: Resolve config via
AGENTS.md: inline@namevault override first, then.env, then the global config (~/.config/obsidian-wiki/config, XDG-style; legacy~/.obsidian-wiki/configstill honored). The resolved config suppliesOBSIDIAN_VAULT_PATH. - Skills:
.skills/contains skill folders, each with aSKILL.mddefining a workflow.
Key Concepts
- The wiki is a compiled artifact — knowledge distilled from raw sources into interconnected pages.
- Every wiki page has YAML frontmatter:
title,category,tags,sources,created,updated. - Pages are connected with Obsidian
[[wikilinks]]. - A
.manifest.jsonin the vault root tracks all ingested sources for delta-based updates. index.mdandlog.mdmust be updated after every operation.
Skills Reference
| Skill | Folder | Purpose |
|---|---|---|
| Setup | .skills/wiki-setup/ |
Initialize vault structure |
| Ingest | .skills/wiki-ingest/ |
Distill documents into wiki pages, plus any text data — chat exports, logs, transcripts |
| History Router | .skills/wiki-history-ingest/ |
Route `/wiki-history-ingest <claude |
| Claude History | .skills/claude-history-ingest/ |
Mine ~/.claude conversations |
| Codex History | .skills/codex-history-ingest/ |
Mine ~/.codex sessions and rollout logs |
| Status | .skills/wiki-status/ |
Audit ingestion state and delta |
| Query | .skills/wiki-query/ |
Answer questions from wiki |
| Context Pack | .skills/wiki-context-pack/ |
Compile bounded vault context for another agent |
| Lint | .skills/wiki-lint/ |
Find broken links, orphans |
| Rebuild | .skills/wiki-rebuild/ |
Archive and rebuild |
| Cross-Linker | .skills/cross-linker/ |
Auto-discover and insert missing wikilinks |
| Tag Taxonomy | .skills/tag-taxonomy/ |
Enforce consistent tag vocabulary |
| LLM Wiki | .skills/llm-wiki/ |
Core architecture pattern |
| Skill Creator | .skills/skill-creator/ |
Create new skills |
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.
- yesterday First seen · 45 lines · 689 tokens per session scan A a1a07ae12d57
obsidian-wiki copilot-instructions.md is an instructions file published in the GitHub repository Ar9av/obsidian-wiki (3,325 stars, last pushed today), licensed MIT. It adds 689 tokens to every session, about $0.0034 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
llm-wiki-agent AGENTS.md
Instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-agent CLAUDE.md
Instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, slash commands (claude code), directory layout, page format and ingest workflow.
llm-wiki-agent GEMINI.md
Instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
memvid CLAUDE.md
Claude Code instructions for memvid/memvid, covering claude.md, project overview, architecture, core components and file format (.mv2).
synto CLAUDE.md
Instructions for kytmanov/synto, covering claude.md, commands, install (editable, auto-detects uv/pip), dependencies and tests (all offline, no ollama required).
llm-wiki-newsroom AGENTS.md
Instructions for alfadur7/llm-wiki-newsroom, covering llm wiki newsroom — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.