Borrowing it
Nothing to install: this file belongs to Szesnasty/Jarvis. 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/Szesnasty/Jarvis/main/CLAUDE.mdgit clone --depth 1 https://github.com/Szesnasty/JarvisWrote 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/szesnasty/jarvis/claude-md)<a href="https://agentmods.dev/instructions/szesnasty/jarvis/claude-md"><img src="https://agentmods.dev/badge/instructions/szesnasty/jarvis/claude-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/szesnasty/jarvis/claude-md"><img src="https://agentmods.dev/badge/instructions/szesnasty/jarvis/claude-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 | $0.05025 | $0.05025 |
| Opus 5 | $0.02513 | $0.02513 |
| Sonnet 5 | $0.01005 | $0.01005 |
| Haiku 4.5 | $0.00502 | $0.00502 |
Grade A, and why
Jarvis CLAUDE.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 — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JARVIS — Full Project Plan
1. What Is Jarvis
Jarvis is a personal memory, planning, and knowledge system**.
It is not:
- A coding tool
- A Claude Code wrapper
- A generic chatbot with memory
It is:
- A voice interface to the user's own local memory
- A personal operating system / second brain / voice memory cockpit
- Built on local Markdown files, compatible with Obsidian
- Powered by Claude API
- Extended with a knowledge graph layer
- Customizable through user-created specialists
Core thesis: AI doesn't remember "on its own" — it works on memory that belongs to the user.
1a. Source of Truth Doctrine
This is a hard rule for the entire codebase:
- Source of truth = Markdown files in
Jarvis/memory/ - SQLite = operational index and cache, never the canonical store. If SQLite is deleted, it must be fully rebuildable from Markdown files.
- Graph = derived layer, rebuildable from memory. If
graph.jsonis deleted, it can be regenerated. - Config =
Jarvis/app/config.jsonfor metadata and flags only.
Every write operation that affects user knowledge must end with a Markdown file on disk. SQLite and graph are acceleration layers, not storage layers.
2. Target Users
- People organizing life, projects, and plans
- People who take lots of notes and want to connect them
- People who want a personal assistant for health, learning, travel, relationships
- Obsidian users (optional power-up)
- Anyone who wants full control over their data and knowledge structure
3. Key Use Cases
A. Weekly Planning
User says: "Plan my week based on recent notes." System searches local memory, considers projects/relations, creates a plan, saves it.
B. Brain Dump → Plan
User dumps chaotic thoughts. System transcribes, organizes, creates a checklist, splits into today/week/later.
C. Conversational Memory Recall
User asks: "What did I decide about vacations?" / "What did I promise Michał?" System searches memory + graph, returns concise answer.
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 · 578 lines · 5,025 tokens per session scan A 648c0e9a0fa4
Jarvis CLAUDE.md is an instructions file published in the GitHub repository Szesnasty/Jarvis (10 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 5,025 tokens to every session, about $0.0251 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
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.
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.