agentmods.dev

signalbox: Instructions file for Claude Code

CLAUDE.md

signalbox CLAUDE.md is an instructions file for Claude Code from dwmkerr/signalbox. It costs 2,528 tokens per session, scanned A, original, MIT.

Project instructions for Signalbox, a local app that shows events from AI coding agents, terminals, and jobs on one board.

In plain words
What is it for?
They guide updates to Signalbox's behavior, command-line interface, event data, agent connections, settings, and other interface specifications, as well as builds and tests.
Why use it?
They keep the written specifications and the software aligned when commands, data formats, adapters, or interface controls change.

Instructions file for Claude Code

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

This is dwmkerr/signalbox's own configuration. It tells Claude Code how to work on signalbox 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 signalbox configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cp hero-anim.gif ../../docs/images/hero-anim.gif.

not rated 20repo 3d ago A scan 2,528 tokens original MIT
View source ↗ dwmkerr/signalbox dwmkerr.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to dwmkerr/signalbox. 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/dwmkerr/signalbox/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dwmkerr/signalbox

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 signalbox CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dwmkerr/signalbox/claude-md"><img src="https://agentmods.dev/badge/instructions/dwmkerr/signalbox/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,528 This file is loaded in full into every session.
When invoked 2,528 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 $0.02528 $0.02528
Opus 5 $0.01264 $0.01264
Sonnet 5 $0.00506 $0.00506
Haiku 4.5 $0.00253 $0.00253

Measured 9d ago against content hash b311dc0d714e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

signalbox 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.

CLAUDE.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

signalbox

A local-first events board for AI coding agents. One board for every agent, terminal, and job you run.

Specs are the source of truth - keep them current

Whenever you change behaviour, update the spec in the same change. The specs in components/specs/ describe the contract; they must never lag the code.

  • components/specs/cli.md - every CLI command, flag, and its output. Update it when you add/rename/remove a command or flag, or change what a command prints.
  • components/specs/events.md - the wire schema (event types, fields, reducer rules). Update it when the event shape or reducer behaviour changes.
  • components/specs/adapters.md - how each agent adapter fires events.
  • components/specs/*.html are the living spec for the app's UI surfaces - the HTML mock IS the source of truth for that surface, not just an illustration:
    • components/specs/settings.html - the Settings window (every control, its label, caption, and the settings-storage table). Change a setting -> update this.
    • components/specs/hub-jumplist.html - the jumplist (rows, keys, footer, marks).
    • components/specs/menubar.html - the menu bar icon + dropdown. When you add/change/remove a control or behaviour on one of these surfaces, update its HTML mock in the same change.

If a change touches behaviour and you did not touch a spec, that is a bug in the change. Treat "code and spec disagree" as a failing state.

Layout

  • components/cli/ - the TypeScript CLI + hub, compiled to a single binary with Bun (bun build --compile). The hub is signalbox hub (same binary).
  • components/app/ - the Swift macOS menu bar app (jumplist, status icon, settings). The app OWNS the hub: it spawns signalbox hub as a child, keeps it alive, and stops it on quit (Hub.swift) - there is no LaunchAgent. The bundle embeds the CLI at Contents/Resources/signalbox. Built via components/app/Makefile (it works around a CommandLineTools SPM manifest bug - use make -C components/app app, not bare swift build; the build target only compiles Swift and leaves a stale CLI in the bundle).
  • components/cli/adapters/ - per-agent hooks/plugins (claude, opencode, pi) and tmux.
  • components/scripts/ - dev helpers (e.g. demo.sh seeds a board via fire).
  • packaging/ - the Homebrew formula template.
  • docs/, components/specs/ - docs site and specs.

Read the full file on GitHub · 200 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. 9d ago First seen · 200 lines · 2,528 tokens per session scan A b311dc0d714e

Subscribe to this mod's changes

signalbox CLAUDE.md is an instructions file published in the GitHub repository dwmkerr/signalbox (20 stars, last pushed 3d ago), licensed MIT. It adds 2,528 tokens to every session, about $0.0126 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.

Claude Codeai-agentscursordeveloper-toolsmacosmenubar
Related

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.

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

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

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens