Borrowing it
Nothing to install: this file belongs to SystemSculpt/obsidian-systemsculpt-ai. 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/SystemSculpt/obsidian-systemsculpt-ai/main/AGENTS.mdgit clone --depth 1 https://github.com/SystemSculpt/obsidian-systemsculpt-aiWrote 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/systemsculpt/obsidian-systemsculpt-ai/agents-md)<a href="https://agentmods.dev/instructions/systemsculpt/obsidian-systemsculpt-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/systemsculpt/obsidian-systemsculpt-ai/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/systemsculpt/obsidian-systemsculpt-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/systemsculpt/obsidian-systemsculpt-ai/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 | $0.02647 | $0.02647 |
| Opus 5 | $0.01324 | $0.01324 |
| Sonnet 5 | $0.00529 | $0.00529 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
obsidian-systemsculpt-ai 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 9d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SystemSculpt AI Obsidian Plugin
Canonical repository guidance for the SystemSculpt Obsidian client. CLAUDE.md is a symlink to this file; edit this file only.
Repository boundary
The SystemSculpt workspace has three sibling repositories:
- ~/gits/systemsculpt/plugin — this Obsidian client.
- ~/gits/systemsculpt/website — the customer website and first-party API.
- ~/gits/systemsculpt/systemsculpt-os — growth and operator automation.
The plugin is a thin, vault-native client. It owns Obsidian integration, presentation, local vault tool implementations, approval UX and enforcement, a reconnecting server-protocol client, user-visible local cache/export state, and portable Studio behavior. It does not own an agent loop, continuation policy, provider retry, compaction, prompt caching, authoritative chat sessions, provider SDKs, provider credentials, model catalogs, marketing operations, or a local AI runtime.
All AI traffic uses the first-party SystemSculpt API at https://systemsculpt.com/api/plugin. OpenRouter and server agent implementation details stay behind that interface.
Server-upgrade independence
This is a release requirement, not an implementation preference:
- The boundary applies to ChatView, Audio Processor, transcription, document processing, images, embeddings, Studio AI, and future managed AI features. The client may capture or select local input bytes, upload them, render progress, obtain local approval, and save or apply a returned result. Provider calls, models, prompts, chunking, polling, retry, transforms, job orchestration, caching, billing, and durable execution state stay server-side.
- Harness, model, provider, retry, caching, compaction, memory, session, and orchestration changes must be deployable server-side without a plugin release.
- The plugin wire contract is harness-agnostic. Production client code, headers, persisted data, UI labels, and tool results must not contain Pi, Think, OpenRouter, AI SDK, or another harness/provider identity.
- The plugin never decides whether the agent should continue. It receives a typed client-tool request, applies local approval policy, executes the Obsidian operation, and returns one typed result. The server decides every subsequent model step.
- The server owns the authoritative conversation session and ordered event history. Local chat persistence is a cache or user export and must never become execution authority after reconnect.
- Client capability negotiation is additive. The plugin advertises supported local tool names and contract versions; the server adapts its tool catalog to that manifest. Unknown additive event fields and unknown server-only tools must not crash or stop the client.
- One migration release may replace the legacy client continuation loop with this thin protocol bridge. The first released thin-client artifact then becomes a permanent compatibility fixture. Every later server agent change must connect, render, execute its supported local tools, reconnect, and finish a long turn against that unchanged artifact.
- A plugin update is justified only by a new or changed local Obsidian capability, a client security correction, or an intentionally new UI feature. A server harness replacement is never sufficient justification.
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.
- 9d ago First seen · 252 lines · 2,647 tokens per session scan A e71d75b65bab
obsidian-systemsculpt-ai AGENTS.md is an instructions file published in the GitHub repository SystemSculpt/obsidian-systemsculpt-ai (193 stars, last pushed 22d ago), licensed MIT. It adds 2,647 tokens to every session, about $0.0132 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.