Claudian is an Obsidian plugin that embeds AI coding agents in a note vault, allowing them to read, edit, search, and manage files there. It is for users who want to work with agents alongside their notes, using features such as inline editing, plans, reusable prompts, and external tool connections.
Borrowing it
Nothing to install: this file belongs to YishenTu/claudian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/YishenTu/claudian/main/AGENTS.mdgit clone --depth 1 https://github.com/YishenTu/claudianWrote 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/yishentu/claudian/agents-md)<a href="https://agentmods.dev/instructions/yishentu/claudian/agents-md"><img src="https://agentmods.dev/badge/instructions/yishentu/claudian/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/yishentu/claudian/agents-md"><img src="https://agentmods.dev/badge/instructions/yishentu/claudian/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00916 | $0.00916 |
| Opus 5.5 | $0.00366 | $0.00366 |
| Sonnet 5.5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
claudian 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 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Loading and verification
- For test changes or changes to the code they cover, follow
tests/AGENTS.md, even when no test edit is planned. - Tests follow the guides of the source they cover; they do not inherit
src/instructions automatically. - Build, dependency, lockfile, locale/static-asset import, and
esbuild.config.mjschanges also requirescripts/AGENTS.md. Composition changes require the guides of the services being wired. - Use the Node version in
.node-version. For code changes, the full verification command is:
npm run typecheck && npm run lint && npm run test && npm run build && npm run check:performance
- For focused changes,
npm run test:affected -- --base origin/mainselects related tests; it does not replace typecheck, lint, build, or performance checks. Documentation-only changes needgit diff --check(CI enforces it on every pull request) and their affected documentation tests, not a production build. - Dev and production builds load
.env.localand may copy artifacts into the configuredOBSIDIAN_VAULT, including removal of its old.codex-vendor. Check that destination before building; clearing the shell variable does not prevent reloading it from the file.
Architectural constraints
src/main.tsis the sole concrete composition root and lifecycle publisher. App subcomposition returns complete domains, never a second root or service locator.src/composition/holds main-owned wiring that must reach bothapp/andfeatures/. Onlymain.tsand other composition modules import it; it never importsmain.tsor concrete providers, andmain.tsstill constructs, registers, and tears it down.- App repositories/settings/storage depend on core contracts, not feature orchestration or provider-native protocols. Concrete provider imports are confined to
main.tsand provider-default assembly. - Features use
FeatureHostand core registries, never concrete app/provider implementations.FeatureHoststays feature-neutral; chat-only capabilities belong in chat'sChatFeatureHostextension. Providers useProviderHost, never feature orchestration. Core imports none of these implementations. - Shared ACP code contains protocol mechanics and protocol-level normalization only; provider launch policy, extensions, provider-specific normalization, and history stay provider-owned.
- Each piece of mutable state or policy has one authoritative owner; other modules read derived projections or call the owner's API. Do not add parallel flags, maps, or guards that must be kept in sync; consolidate into the owner instead. Code that only looks alike under different provider semantics is not shared policy.
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 Changed · +1 lines · +47 tokens per session 1e8567acb966
- 22d ago Changed · +1 lines · +61 tokens per session 32ab30581760
- 1mo ago Changed · +1 lines · +28 tokens per session 312336cd7f50
- 1mo ago Changed · -3 lines · -18 tokens per session 55fd0f2d473f
- 1mo ago Changed · -9 lines · -172 tokens per session 37387c168f05
- 1mo ago Changed · -9 lines · -194 tokens per session f4171de8e2e4
- 1mo ago Changed · +4 lines · +110 tokens per session a61acad0c95f
- 1mo ago Changed · -101 lines · -1,354 tokens per session 5b825d63fb66
- 1mo ago Changed · -3 tokens per session 0ca56f21c0eb
- 1mo ago First seen · 156 lines · 2,411 tokens per session scan A 135505d82362
claudian AGENTS.md is an instructions file published in the GitHub repository YishenTu/claudian (15,813 stars, last pushed yesterday), licensed MIT. It adds 916 tokens to every session, about $0.0037 per session on Opus 5.5. 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
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.