Obsidian YOLO is an AI assistant integrated with Obsidian for chatting, writing, learning, and managing a knowledge base. It is for people who use Obsidian as a workspace for notes and personal knowledge. Catalogue add-ons provide related assistant capabilities.
Borrowing it
Nothing to install: this file belongs to Lapis0x0/obsidian-yolo. 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/Lapis0x0/obsidian-yolo/main/AGENTS.mdgit clone --depth 1 https://github.com/Lapis0x0/obsidian-yoloWrote 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/lapis0x0/obsidian-yolo/agents-md)<a href="https://agentmods.dev/instructions/lapis0x0/obsidian-yolo/agents-md"><img src="https://agentmods.dev/badge/instructions/lapis0x0/obsidian-yolo/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/lapis0x0/obsidian-yolo/agents-md"><img src="https://agentmods.dev/badge/instructions/lapis0x0/obsidian-yolo/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 | $0.02526 | $0.02526 |
| Opus 5.5 | $0.01010 | $0.01010 |
| Sonnet 5.5 | $0.00505 | $0.00505 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
obsidian-yolo 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 29d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
YOLO is an Obsidian plugin for AI chat, agent workflows, RAG, writing assistance, and independently shipped product modules such as FSRS-based Learning and the Whiteboard infinite canvas.
For a behavior ↔ code-location ↔ verification-path index (complements this file's directory-ownership rules, doesn't restate them), see FEATURE_MAP.md.
Commands
Verify what you touched: host code → type-check + relevant tests; module code → module typecheck, tests, npm --prefix modules/<id> run test:boundary when available, and module build; runtime component code → runtime typecheck, tests, build, and verify; host CSS → styles build (module CSS is rebuilt by the module build).
npm run dev- Build runtime components and first-party modules, then watch the host app, host styles, and dev-vault artifactsnpm run build- Production build with host, module, and runtime component type checking; run for changes affecting production bundling, module boundaries, runtime loading, or cross-platform behaviornpm run type:check/npm run module:typecheck/npm run runtime:typecheck- Type-check the host, first-party modules, or runtime componentsnpm run module:build- Rebuild first-party module artifacts and the bundled module catalognpm run runtime:build/npm run runtime:verify- Rebuild runtime component artifacts and their registry, or verify the host bundle doesn't statically pull in a runtime component's dependenciesnpm run lint:check/npm run lint:fix- Check or fix Prettier and ESLintnpm test- Run the full Jest suite; usenpx jest <test-file> --runInBandfor serial debuggingnpm run styles:build- Regenerate the hoststyles.cssfromsrc/styles/**npm run deps:check- Enforce the circular-dependency ratchet; after removing cycles, tighten the baseline withnpm run deps:baseline
Architecture
src/main.tsowns the host plugin lifecycle.src/ChatView.tsxandsrc/components/chat-view/own the main chat surface.src/core/modules/owns module discovery, installation, loading, activation, lifecycle, and the versioned Host API.modules/host-sdk.d.tsis the module-facing API contract.modules/<id>/owns everything in a product module: its UI, domain logic, host adapters, styles, assets, workers, and tests.modules/learning/andmodules/whiteboard/hold the complete Learning and Whiteboard implementations.src/core/runtime-components/owns discovery, download, and lifecycle of on-demand runtime components.runtime-components/<id>/at the repo root owns each component's source and build output;runtime-components/sdk.d.tsis the component-facing contract.src/core/agent/owns the shared native agent runtime, tool gateway, conversation service, subagents, and background tasks.NativeAgentRuntimeis the one orchestration; its consumers areAgentSessionService(chat surfaces),AgentRunApiinagent-api.ts(programmatic callers, modules included), andsubagent/runner.ts. A caller without a chat view goes throughagent-api.tsand states a trust tier ascapability(none/vault-read/vault-write, incapability-profile.ts) instead of hand-assembling tools or anAgentSessionService.runinput; chat modes resolve throughresolveChatModeRuntime(chat-runtime-profiles.ts).src/core/cli-runtime/owns the external CLI agent runtimes the chat surface can switch to. They are a separate execution surface alongsideAgentSessionService, not a second orchestration of it, and are desktop-only — keep their implementations out of the mobile static graph.src/core/ai/single-turn.tsis the low-latency path for Sparkle (tab completion, selection rewrite, continuation). Do not route these features through the agent runtime.src/core/tools/owns every built-in tool:capabilities/is the single registration point, and the tool catalog, settings rows, approval policy, persisted keys, and the chat summary classification are all derived from it — never add a side table.dispatcher.tsis the only execution path. Deferred disclosure is the only mode: a tool outside the request'stoolsarray is reached through the protocol-internalinvoke_tool/load_tool_schemas, which carry no capability and never appear in settings. Evaluate approval and every other per-tool policy against the unwrapped call, never the wrapper.src/core/llm/,auth/,rag/,mcp/, andskills/own shared model, provider, retrieval, and MCP capabilities.src/features/contains host-shipped cross-cutting features.src/database/,src/settings/, andsrc/styles/own host persistence, settings, and global styles.
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.
- 29d ago Changed · +52 tokens per session 2cdac41a5d36
- 1mo ago Changed · +1 lines · +57 tokens per session 96f8fdcce02e
- 1mo ago Changed · +104 tokens per session 35af0508e86e
- 1mo ago Changed · +5 tokens per session 68dbaaeeda6a
- 1mo ago Changed · +2 lines · +198 tokens per session dda3b2f62a67
- 1mo ago First seen · 88 lines · 2,110 tokens per session scan A 540b929cd853
obsidian-yolo AGENTS.md is an instructions file published in the GitHub repository Lapis0x0/obsidian-yolo (1,376 stars, last pushed yesterday), licensed MIT. It adds 2,526 tokens to every session, about $0.0101 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.