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/t-rhex/obsidian-mcp-server/agents-mdgit clone --depth 1 https://github.com/t-rhex/obsidian-mcp-serverWrote 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/t-rhex/obsidian-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/t-rhex/obsidian-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/t-rhex/obsidian-mcp-server/agents-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 | $0.00836 | $0.00836 |
| Opus 5 | $0.00418 | $0.00418 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
obsidian-mcp-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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-obsidian-vault
Build & Test
npm install && npm run build
npm test # 375 integration tests (node test/run.mjs)
npm run dev # tsc --watch
Architecture
27 MCP tools: 10 vault + 7 task/project + 3 context + 4 agent/review + 3 usage/timeout.
TypeScript ES modules, Node ≥ 18. Ships as npx mcp-obsidian-vault.
Key deps: @modelcontextprotocol/sdk v1.x, zod v4, gray-matter.
src/index.ts — MCP server entry, tool + prompt registration
src/tools/*.ts — one file per tool (27 files)
src/config.ts — env var parsing (vault, git, webhooks, folders)
src/errors.ts — ErrorCode enum, VaultError, safeToolHandler wrapper
src/vault.ts — filesystem ops: path safety, atomic writes, list, search
src/frontmatter.ts — YAML frontmatter parse/serialize, tag extraction
src/git.ts — git CLI wrapper with mutex lock
src/events.ts — EventBus with typed task lifecycle events
src/webhooks.ts — WebhookEmitter with HMAC-SHA256 signing
src/agent-registry.ts — agent profiles, scanning, capability matching
src/task-schema.ts — task types, ID gen, validation, body template
src/task-dashboard.ts — scan tasks, generate DASHBOARD.md
Tool Categories
Vault (10 tools)
read_note, create_note, update_note, delete_note, search_vault, list_vault, manage_tags, daily_note, wikilinks, git_sync
Task Orchestration (7 tools)
create_task, list_tasks, claim_task, update_task, complete_task, create_project, get_project_status
Context Persistence (3 tools)
get_context, log_decision, log_discovery
Review & HITL (1 tool)
review_task — approve/reject/request_changes on tasks with review_required
Agent Management (3 tools)
register_agent, list_agents, suggest_assignee
Timeout & Usage (3 tools)
check_timeouts, log_usage, get_usage_report
Task State Machine
pending → claimed → in_progress → completed
→ in_progress → needs_review → completed (approve)
→ revision_requested → in_progress (revise)
→ in_progress → failed
blocked → pending (auto-unblock when deps complete)
completed/failed/cancelled → pending (reopen/retry)
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.
- 5d ago First seen · 89 lines · 836 tokens per session scan A b6f48db8cd45
obsidian-mcp-server AGENTS.md is an instructions file published in the GitHub repository t-rhex/obsidian-mcp-server (2 stars, last pushed 6mo ago), licensed MIT. It adds 836 tokens to every session, about $0.0042 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.
Other instructions, from other repositories
llm-wiki-compiler AGENTS.md
AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.
pi-llm-wiki AGENTS.md
AGENTS.md instructions for zosmaai/pi-llm-wiki, covering agents.md, project, tech stack, file layout and conventions.
DeepPaperNote AGENTS.md
AGENTS.md instructions for 917Dhj/DeepPaperNote, covering deeppapernote agent guide, repository purpose, canonical sources, non-negotiable product invariants and repository structure.
DeepPaperNote CLAUDE.md
Claude Code instructions for 917Dhj/DeepPaperNote, covering claude code integration and skill invocation.
hippocampus CLAUDE.md
Instructions for sturlese/hippocampus, covering layout, frontmatter schema, conventions, answering questions from the vault (read order) and contradictions.
kimun CLAUDE.md
Instructions for nico2sh/kimun, covering kimun, docs and rules.