vibepulse: Instructions file for Claude Code

CLAUDE.md

vibepulse CLAUDE.md is an instructions file for Claude Code from niclasvestlund-YT/vibepulse. It costs 1,167 tokens per session, scanned A, original, MIT.

Project instructions for Vibepulse, a hardware project with firmware, a device update process, logs, releases, and display work. They explain how to work with the repository and update the device over the air, meaning through its network connection.

In plain words
What is it for?
Use them when building firmware, preparing an over-the-air update, inspecting logs and errors, working with device hardware, or preparing a release.
Why use it?
They reduce the risk of using an old build, updating the device at the wrong time, or overlooking required recovery and troubleshooting steps.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is niclasvestlund-YT/vibepulse's own configuration. It tells Claude Code how to work on vibepulse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibepulse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to niclasvestlund-YT/vibepulse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/niclasvestlund-YT/vibepulse/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/niclasvestlund-YT/vibepulse

Made for: Claude Code.

Wrote 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.

agentmods badge for vibepulse CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/niclasvestlund-yt/vibepulse/claude-md/github.svg)](https://agentmods.dev/instructions/niclasvestlund-yt/vibepulse/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/niclasvestlund-yt/vibepulse/claude-md"><img src="https://agentmods.dev/badge/instructions/niclasvestlund-yt/vibepulse/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.

agentmods 80×15 button for vibepulse CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/niclasvestlund-yt/vibepulse/claude-md"><img src="https://agentmods.dev/badge/instructions/niclasvestlund-yt/vibepulse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,167 This file is loaded in full into every session.
When invoked 1,167 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01167 $0.01167
Opus 5 $0.00583 $0.00583
Sonnet 5 $0.00233 $0.00233
Haiku 4.5 $0.00117 $0.00117

Measured 4d ago against content hash b5bc51c46358, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vibepulse 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.

CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read README.md for the repository structure and build workflow.

Follow CONTRIBUTING.md and docs/maintaining-contributions.md for contributions and merging. Maintainer changes also go through a PR with passing required checks. Documented local test omissions do not waive GitHub's merge requirements.

Setting this repo up for someone (secrets, build, flash, tokenserver)? Follow docs/agent-setup.md — step-by-step, with verifications and a symptom→fix table. Never flash the board without the user explicitly asking you to.

Over-the-air updates

Day-to-day firmware goes over the air: idf.py build && tools/ota-flash.sh (device IP from git-ignored .ota-device). The full loop, consent model and troubleshooting live in docs/ota.md — read it before touching anything OTA. Non-negotiables: the maintenance window opens ONLY from the device (a 3 s KEY3 hold opens SETTINGS, where UPDATE opens it — greyed out without an address, since a window with no address cannot receive an upload; WIFI opens the setup window, see docs/wifi.md — or the UPDATE pill on the takeover) — never claim or imply a script can; the sender gates (newest-binary-at-send, version printed, -dirty refused) exist because a stale archived build once froze the panel — never bypass them with TG_OTA_ALLOW_DIRTY without the user saying so; and after editing tools/tokenserver/, restart the host service (macOS: launchctl kickstart -k gui/$(id -u)/se.torget.tokenserver; Windows has no launchd — the service runs under Task Scheduler, so restart it with Stop-ScheduledTask, a wait until it has actually stopped, and only then Start-ScheduledTask on the task VibePulse tokenserver; the task is registered -MultipleInstances IgnoreNew, so an immediate start is silently discarded and the service stays down until the five-minute watchdog — the snippet is under "Restarting the scheduled task" in docs/windows-setup.md. Never restart it by rerunning install-windows-task.ps1, which rebuilds the task's command line from that invocation's arguments and so silently drops the -PublishUrl, -GithubRepo and plan/cost settings it was installed with) — the running process keeps old code and the panel honestly shows the gap.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 4d ago Changed · +4 lines · +52 tokens per session b5bc51c46358
  2. 5d ago Changed · +10 lines · +163 tokens per session a864f847efac
  3. 6d ago Changed · +1 lines · +15 tokens per session e86100a362d5
  4. 13d ago First seen · 73 lines · 937 tokens per session scan A b393232856cc

Subscribe to this mod's changes

vibepulse CLAUDE.md is an instructions file published in the GitHub repository niclasvestlund-YT/vibepulse (194 stars, last pushed yesterday), licensed MIT. It adds 1,167 tokens to every session, about $0.0058 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens