Use it when documenting, building, or modifying this Obsidian plugin, especially its catalog, local server, routing, resource serving, and security behavior.

It gives contributors the project’s architecture, terminology, and required rules in one place before they change the code.

How dsebastien/obsidian-agentic-resource-discovery-server configures C

Q: What is obsidian-agentic-resource-discovery-server AGENTS.md?

Project instructions for an Obsidian plugin that publishes skills and agent resources from a local vault. It creates a searchable catalog and serves resources through local REST and MCP interfaces.

Reuse

Borrowing it

Nothing to install: this file belongs to dsebastien/obsidian-agentic-resource-discovery-server. 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/dsebastien/obsidian-agentic-resource-discovery-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dsebastien/obsidian-agentic-resource-discovery-server

Made for: Codex, OpenCode.

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/dsebastien/obsidian-agentic-resource-discovery-server/agents-md/github.svg)](https://agentmods.dev/instructions/dsebastien/obsidian-agentic-resource-discovery-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dsebastien/obsidian-agentic-resource-discovery-server/agents-md"><img src="https://agentmods.dev/badge/instructions/dsebastien/obsidian-agentic-resource-discovery-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dsebastien/obsidian-agentic-resource-discovery-server/agents-md"><img src="https://agentmods.dev/badge/instructions/dsebastien/obsidian-agentic-resource-discovery-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11,230 This file is loaded in full into every session.

When invoked 11,230 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 94% copy Near-identical to another mod 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	$0.11230	$0.11230
Opus 5.5	$0.04492	$0.04492
Sonnet 5.5	$0.02246	$0.02246
Haiku 4.5	$0.01123	$0.01123

Measured 1mo ago against content hash 71274c50202a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obsidian-agentic-resource-discovery-server 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 1mo 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.

Origin

This is a copy

94% identical to obsidian-transcriber AGENTS.md — 116 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 808 lines

How it starts

The opening of the file, as written. The whole thing — 808 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This project: obsidian-agentic-resource-discovery-server

Read this first. It orients you in this codebase; the generic template guidance follows below.

What it is. An Obsidian plugin (isDesktopOnly) that turns the vault into a local-first Agentic Resource Discovery (ARD) publisher + Agent Registry: it scans AI Skills into an ai-catalog.json and serves it (REST + MCP) on 127.0.0.1 so local AI agents can search and fetch resources.

Start here.

documentation/Architecture.md — module map + data flow.
documentation/Domain Model.md — the ubiquitous language. Use these terms exactly.
documentation/Business Rules.md — invariants (BR-1…BR-15). Treat as mandatory; e.g. loopback-only bind, auth-except-public-catalog, traversal-safe file serving, sandbox isolation.

How the code is shaped (deep modules, tested through their interface).

The HTTP layer is split: server/router.ts is a pure RegistryRequest → RegistryResponse function (all endpoint behaviour, fully unit-tested without sockets); server/http-server.ts is a thin node:http adapter over it. Don't put behaviour in the adapter.
server/registry-controller.ts is the only seam the plugin drives (start/stop/rebuild/setSkillEntries). It owns the catalog, the SearchBackend, the SkillFileService, and the server. The router closes over a mutable RouterDeps, so a rebuild swaps the catalog in place.
Pluggable seams: SearchBackend (search/search-backend.ts, default lexical-search-backend.ts, built via search-backend-factory.ts) and SkillFileService (skills/skill-file-server.ts). Add new behaviour as a new implementation, not a flag.
The MCP endpoint (mcp/) is hand-rolled JSON-RPC (not @modelcontextprotocol/sdk) + a QuickJS WASM Code Mode sandbox (mcp/sandbox.ts).

Conventions specific to this repo.

Test-first (TDD), verify on real data. Write the *.spec.ts red→green per module; run a single file with bun test <path>. The scanner/enricher are verified against the real ~395-skill vault at /c/users/trankill/My Drive/Notes/Seb/.claude/skills — a real-data smoke test already caught a Date.slice bug that unit tests missed.
Frontmatter is untrusted. js-yaml turns unquoted dates into Date objects and yields numbers/booleans; always coerce via asString/asStringArray (see skills/skill-enricher.ts) before string ops. Do not reintroduce gray-matter — it calls yaml.safeLoad, removed in the repo's pinned js-yaml@4.
Lint gotchas: plugin lifecycle methods return void (not Promise) — fire-and-forget with void; use window.setTimeout, never bare setTimeout; avoid NodeJS.* type references (no-undef); no String(unknown) (no-base-to-string) — narrow with typeof x === 'string'. Specs follow the same rules as production code (no any, no rule switched off for them): type response bodies with the production types, and use Bun.fetch for tests that hit the real local HTTP server.
Always finish a change green: bun run validate (tsc + tests + lint) and bun run build. Keep the plan's §1a status table updated and commit per milestone with a conventional-commit message (allowed scopes: all/build/deps/docs/plugin).

Read the full file on GitHub · 808 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.

1mo ago Changed · +33 lines · +879 tokens per session 71274c50202a
1mo ago Changed · +3 lines · +343 tokens per session fa2943c972f1
2mo ago First seen · 772 lines · 10,008 tokens per session scan A af72b5834124

Subscribe to this mod's changes

obsidian-agentic-resource-discovery-server AGENTS.md is an instructions file published in the GitHub repository dsebastien/obsidian-agentic-resource-discovery-server (7 stars, last pushed 24d ago), licensed MIT. It adds 11,230 tokens to every session, about $0.0449 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to obsidian-transcriber AGENTS.md, differing in 116 lines, and is treated as a copy.

Building agents ai ai-agents aiskills mcp obsidian obsidian-plugin

obsidian-agentic-resource-discovery-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
obsidian-agentic-resource-discovery-server AGENTS.mddsebastien/obsidian-agentic-resource-discovery-server	Instructions file	7	24d ago	MIT	A	11,230	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

obsidian-agentic-resource-discovery-server: Instructions file for Codex