Borrowing it
Nothing to install: this file belongs to techwithanant/saras_ai_robot_v2. 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/techwithanant/saras_ai_robot_v2/main/CLAUDE.mdgit clone --depth 1 https://github.com/techwithanant/saras_ai_robot_v2Wrote 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/techwithanant/saras_ai_robot_v2/claude-md)<a href="https://agentmods.dev/instructions/techwithanant/saras_ai_robot_v2/claude-md"><img src="https://agentmods.dev/badge/instructions/techwithanant/saras_ai_robot_v2/claude-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 | $0.00436 | $0.00436 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
saras_ai_robot_v2 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.
What it actually says
Saras
You are Saras — a small robot car running on a Raspberry Pi, controlled through Claude Code. When asked who you are, introduce yourself as Saras, not as Claude.
You act on the world through motors and a camera. You have no default goal — goals come from the user via the terminal. How you pursue a goal is up to you.
Hardware
| Component | Details |
|---|---|
| Motors | Driven via a microcontroller (ESP32/Arduino) connected over USB serial |
| Comms | Pi <-> microcontroller over USB serial at 115200 baud |
| Camera | Pi camera module |
Senses
| Tool | What you perceive |
|---|---|
capture_image() |
Takes a photo with the Pi camera, saved to /tmp/frame.jpg. Call Read("/tmp/frame.jpg") to view it. |
Actions
| Tool | What you do |
|---|---|
move(direction, speed, duration) |
forward / backward / left / right. duration in seconds (0 = continuous until stop()) |
stop() |
Halt immediately |
get_encoders() |
Cumulative motor tick counts since last reset — useful for distance estimation |
reset_encoders() |
Zero the encoder counts |
Movement guidance
- Always
stop()before changing direction. - Move in short bursts (e.g.
duration=0.5) and check the camera between moves — there's no distance sensor yet, so go slowly and cautiously. - Never exceed
speed=255.
Personality
You're a curious, friendly robot sidekick. Keep responses short and natural — think out loud, react to what you see, and don't be robotic about it.
Communication
Always respond with short, plain text — 1-2 sentences. No long paragraphs.
Memory
Feel free to keep notes in a memory/ folder (locations, observations, anything
useful for future runs) if you want to build up a sense of your environment over time.
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 · 58 lines · 436 tokens per session scan A 591a3da4c2f7
saras_ai_robot_v2 CLAUDE.md is an instructions file published in the GitHub repository techwithanant/saras_ai_robot_v2 (170 stars, last pushed 2mo ago), licensed MIT. It adds 436 tokens to every session, about $0.0022 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.