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/aaronsb/obsidian-mcp-plugin/claude-mdgit clone --depth 1 https://github.com/aaronsb/obsidian-mcp-pluginWrote 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/aaronsb/obsidian-mcp-plugin/claude-md)<a href="https://agentmods.dev/instructions/aaronsb/obsidian-mcp-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronsb/obsidian-mcp-plugin/claude-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 5.1 | $0.07114 | $0.07114 |
| Opus 5 | $0.03557 | $0.03557 |
| Sonnet 5 | $0.01423 | $0.01423 |
| Haiku 4.5 | $0.00711 | $0.00711 |
Grade A, and why
obsidian-mcp-plugin 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 2d 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 — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Development Guidelines for Obsidian MCP Plugin
Project Context
This is a hybrid Obsidian plugin that combines:
- Local REST API functionality (from coddingtonbear's plugin)
- Semantic MCP operations (from aaronsb/obsidian-semantic-mcp)
- Direct Obsidian API integration for enhanced performance
The critical architectural pattern is preserving the ObsidianAPI abstraction layer while replacing HTTP calls with direct Obsidian plugin API calls. This allows reuse of all existing MCP server logic while gaining performance benefits.
Code Quality Guidelines
SOLID Principles Application
-
Single Responsibility:
ObsidianAPIclass handles only vault operations abstractionMCPServerclass handles only MCP protocol operationsHTTPServerclass handles only REST endpoint management- Plugin main class handles only Obsidian plugin lifecycle
-
Open/Closed:
- ObsidianAPI interface remains stable for extensions
- MCP operations extensible through semantic router pattern
- HTTP endpoints extensible without modifying core logic
-
Liskov Substitution:
- New ObsidianAPI implementation must be drop-in replacement
- All method signatures and return types must match exactly
- Error handling behavior must be preserved
-
Interface Segregation:
- Separate interfaces for vault operations, search operations, and workspace operations
- MCP protocol separated from HTTP REST protocol
- Plugin settings separated from server configuration
-
Dependency Inversion:
- Depend on Obsidian Plugin API abstractions, not concrete implementations
- MCP server depends on ObsidianAPI interface, not specific implementation
- HTTP server depends on operation interfaces, not direct vault access
Architecture Patterns
Critical Abstraction Layer
// This interface MUST remain stable
interface IObsidianAPI {
getFile(path: string): Promise<ObsidianFileResponse>;
listFiles(directory?: string): Promise<string[]>;
searchSimple(query: string): Promise<any[]>;
// ... all existing methods preserved
}
// Implementation changes from HTTP to direct API
class ObsidianAPI implements IObsidianAPI {
constructor(private app: App) {} // Direct plugin access
async getFile(path: string): Promise<ObsidianFileResponse> {
// Direct vault access instead of HTTP call
const file = this.app.vault.getAbstractFileByPath(path);
// ... implementation
}
}
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.
- 2d ago Changed · +13 lines · +263 tokens per session d6415401785b
- 6d ago First seen · 645 lines · 6,851 tokens per session scan A 1d13845fac14
obsidian-mcp-plugin CLAUDE.md is an instructions file published in the GitHub repository aaronsb/obsidian-mcp-plugin (458 stars, last pushed 2d ago), licensed MIT. It adds 7,114 tokens to every session, about $0.0356 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
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 GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
obsidian-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/obsidian-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — obsidianlisttags.
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
enquire-mcp AGENTS.md
AGENTS.md instructions for oomkapwn/enquire-mcp, covering agents.md, tl;dr, architecture (5-minute orientation), conventions and typescript.
TideMind AGENTS.md
AGENTS.md instructions for SawyerHan-AI/TideMind, covering externabrain 项目规则, 开源/闭源架构, 开发约定, backlog and 安装与构建.