What is ayontclaudian CLAUDE.md?

Project instructions for ayontclaudian, an Obsidian plugin that embeds coding-agent command-line tools inside an Obsidian vault, where the agents can read and edit notes and run commands.

Use them when changing ayontclaudian so new behavior follows its language, code, testing, documentation, and production-code conventions.

They record project architecture and rules that are easy to miss, including German user-facing text, English code, and test-first development (TDD).

How Ayont/ayontclaudian configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to Ayont/ayontclaudian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Ayont/ayontclaudian/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Ayont/ayontclaudian

Made for: Claude Code, Codex.

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/instructions/ayont/ayontclaudian/claude-md.svg)](https://agentmods.dev/instructions/ayont/ayontclaudian/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ayont/ayontclaudian/claude-md"><img src="https://agentmods.dev/badge/instructions/ayont/ayontclaudian/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,911 This file is loaded in full into every session.

When invoked 2,911 The same file — it is already loaded in full.

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	$0.02911	$0.02911
Opus 5	$0.01456	$0.01456
Sonnet 5	$0.00582	$0.00582
Haiku 4.5	$0.00291	$0.00291

Measured 7d ago against content hash 950fda2f5c00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ayontclaudian CLAUDE.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 7d 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.

CLAUDE.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

ayontclaudian (Ayont/ayontclaudian) embeds coding-agent CLIs as chat runtimes directly inside an Obsidian vault. The vault is the agent's working directory: it reads and writes notes, searches, runs bash, and drives agentic workflows in place.

This is a fork of YishenTu/claudian that has diverged substantially. It is not in the Obsidian community registry — it ships via GitHub releases and BRAT.

Plugin id: realclaudian · display name: ayontclaudian · author: Ayont
Deployed folder in a vault: .obsidian/plugins/realclaudian/

Conventions that are easy to get wrong

User-facing strings are German. Chat copy, notices, settings descriptions, GUI labels. Code — identifiers, comments, commit messages, docs — is English. There are 10 locale files under src/i18n/locales/, but German is the product voice; new UI text should be written in German unless it is a code-level label.
Comment why, not what. No narration, no redundant JSDoc.
No console.* in production code.
TDD for behavior changes: failing test first in the mirrored tests/ path.
Throwaway scripts and handoff notes go in .context/ (git-ignored), not dev/.

Providers (12)

Every provider is a directory under src/providers/<id>/ plus two calls in src/providers/index.ts and one entry in defaultProviderConfigs.ts. ProviderId is a bare string (src/core/types/provider.ts) — there is no union to extend. What differs between providers is the transport shape:

Provider	Integration shape
`claude`	Official Claude Agent SDK (`@anthropic-ai/claude-agent-sdk`). Full-feature reference implementation.
`codex`	`codex app-server` over JSON-RPC, plus JSONL transcript reload
`opencode`	ACP (shared code in `src/providers/acp/`)
`hermes`	ACP (`hermes acp`); model catalog + modes come from `session/new`, history from `~/.hermes/state.db`
`cline`	`--print`, plus the `/goal` verification loop (see below)
`kimi`	`--print` + full-message NDJSON, plus an ACP runtime
`vibe`	`--print` + full-message NDJSON
`grok`	`--print` + delta JSON with resume
`dsh`	`--print`
`antigravity`	`agy --print`, single-shot; state recovered by tailing `transcript.jsonl`
`pi`	`--print`
`freebuff`	HTTP + SSE against the local desktop app (no child process)

Read the full file on GitHub · 207 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.

7d ago First seen · 207 lines · 2,911 tokens per session scan A 950fda2f5c00

Subscribe to this mod's changes

ayontclaudian CLAUDE.md is an instructions file published in the GitHub repository Ayont/ayontclaudian (4 stars, last pushed today), licensed MIT. It adds 2,911 tokens to every session, about $0.0146 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.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

ayontclaudian: Instructions file for Claude Code