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 plugins/agricidaniel/claude-obsidian/marketplace/plugin marketplace add AgriciDaniel/claude-obsidiangit clone --depth 1 https://github.com/AgriciDaniel/claude-obsidianGrade A, and why
agricidaniel-claude-obsidian 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.
What it actually says
{
"description": "Audited public distribution channel for claude-obsidian",
"name": "agricidaniel-claude-obsidian",
"owner": {
"name": "AgriciDaniel"
},
"plugins": [
{
"author": {
"name": "AgriciDaniel",
"url": "https://github.com/AgriciDaniel"
},
"description": "Local-first Agent Skills package and Claude Code plugin for source-cited Obsidian knowledge bases. Includes recoverable transactions, deterministic lint and retrieval, provenance ledgers, explicit vault adoption, offline-first capture foundations, and methodology modes.",
"homepage": "https://github.com/AgriciDaniel/claude-obsidian",
"license": "MIT",
"name": "claude-obsidian",
"repository": "https://github.com/AgriciDaniel/claude-obsidian",
"source": "./"
}
],
"version": "2.1.1"
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 23 lines scan A 6984752e225e
agricidaniel-claude-obsidian is a plugin published in the GitHub repository AgriciDaniel/claude-obsidian (14,464 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
claude-canvas
AI-orchestrated visual production for Obsidian Canvas. Create presentations, flowcharts, mood boards, knowledge graphs, and galleries with intelligent layout and AI-generated content.
llm-brain
raw/ 소스를 wiki/로 컴파일하는 개인 지식 위키 컴파일러 + OKF v0.1 export 포트. ingest(4채널)·curate(점진 압축·그래프·메타점수)·express·query·okf·doctor(설치 진단)·wikiweb(웹 UI) 커맨드 + Agent Memory OS 5층 기억(작업·에피소드·의미·절차·메타). LLM을 컴파일러로 쓰는 Karpathy 패턴 + Forte CODE.
llm-brain
Plugin marketplace listing 1 plugin: llm-brain.
second-brain
Battle-tested Claude Code skills from a live second-brain and AI-cofounder operation at Palo Alto AI Research Lab: quality gates, retrospectives, memory and recall, fleet coordination. Method, not data.
second-brain-skills
101 battle-tested Claude Code skills from a live second-brain + assistant operation. Quality gates, retrospectives, CRM, vault ingest, multi-model review panels, fleet coordination. Method, not data.
model-router
Run Claude Code sessions, workers, and subagents on any model your subscriptions cover - one local proxy, zero API keys. Ships the /fabsol orchestrator + worker build flow.