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/ovr/vibecoder-connector/claude-mdgit clone --depth 1 https://github.com/ovr/vibecoder-connectorWrote 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/ovr/vibecoder-connector/claude-md)<a href="https://agentmods.dev/instructions/ovr/vibecoder-connector/claude-md"><img src="https://agentmods.dev/badge/instructions/ovr/vibecoder-connector/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 | $0.00446 | $0.00446 |
| Opus 5 | $0.00223 | $0.00223 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
vibecoder-connector 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 4d 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
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A Claude Code plugin that delivers haptic feedback through Buttplug-compatible devices (via Intiface Central) during coding sessions. When Claude needs attention, finishes a task, or starts a session, connected devices vibrate with distinct patterns.
Prerequisites
- Intiface Central must be running with its WebSocket server on
ws://127.0.0.1:12345(default) - At least one vibrating device paired in Intiface Central
- Node.js (ESM — the project uses
"type": "module")
Commands
npm install # install dependencies
node scripts/vibrate.js --pattern=<name> # trigger a pattern manually (hello, attention, complete)
No build step, no tests, no linter configured.
Architecture
This is a Claude Code plugin, not a standalone app. The entry point is .claude-plugin/plugin.json, which registers hooks defined in hooks/hooks.json.
Hook flow:
SessionStart(startup/resume) -> fireshellopattern (double tap)Notification(permission_prompt/idle_prompt/elicitation_dialog) -> firesattentionpattern (slow wave)Stop-> firescompletepattern (celebratory burst)
Each hook runs scripts/vibrate.js --pattern=<name> asynchronously with a 10s timeout.
scripts/vibrate.js — the single runtime script. Connects to Intiface Central via the buttplug npm package's WebSocket connector, discovers vibrating devices, plays the requested pattern (sequence of intensity+duration steps), then disconnects. Exits with code 0 on all errors to avoid blocking Claude Code.
config/patterns.json — defines vibration patterns as arrays of {intensity, ms} steps, plus intifaceUrl and intensityMultiplier (0-1 global scaling). Add new patterns here; they're immediately available via --pattern=<name>.
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.
- 4d ago First seen · 38 lines · 446 tokens per session scan A a2c57377a017
vibecoder-connector CLAUDE.md is an instructions file published in the GitHub repository ovr/vibecoder-connector (16 stars, last pushed 5mo ago), licensed MIT. It adds 446 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
claude-ros2-skills CLAUDE.md
Claude Code instructions for Leehyunbin0131/claude-ros2-skills, covering read this first — ros 2 verification protocol, establish before writing (no doc can tell you these) and done means it ran.
m5stack-skills CLAUDE.md
Instructions for iot-forge/m5stack-skills, covering working in this repo, layout, two rules that fail silently, building or updating a skill and writing style for skills.
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
embedded-systems-architect GEMINI.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…