git-watchtower: Instructions file for Claude Code

CLAUDE.md

git-watchtower CLAUDE.md is an instructions file for Claude Code from drummel/git-watchtower. It costs 573 tokens per session, scanned A, original, MIT.

Project instructions for git-watchtower, a terminal tool that monitors Git branches with activity sparklines and can run a development server with live reload. They document setup, tests, type checking, and commit rules.

In plain words
What is it for?
Use them when developing git-watchtower, running its checks, or writing Conventional Commits messages that control automatic versioning.
Why use it?
They give a coding agent the project context and the rules needed to make compatible changes and releases.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is drummel/git-watchtower's own configuration. It tells Claude Code how to work on git-watchtower 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 git-watchtower configures →

Reuse

Borrowing it

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

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 git-watchtower CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/drummel/git-watchtower/claude-md"><img src="https://agentmods.dev/badge/instructions/drummel/git-watchtower/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 573 This file is loaded in full into every session.
When invoked 573 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 $0.00573 $0.00573
Opus 5.5 $0.00229 $0.00229
Sonnet 5.5 $0.00115 $0.00115
Haiku 4.5 $0.00057 $0.00057

Measured 2mo ago against content hash e14ad7c0a317, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-watchtower 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 2mo 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

git-watchtower is a terminal-based Git branch monitor with activity sparklines and an optional dev server with live reload. It's a zero-dependency Node.js CLI application.

Development

  • Entry point: bin/git-watchtower.js
  • Node.js: Requires >= 20.0.0 (recursive fs.watch for live-reload relies on Node 20+)
  • Dependencies: None (zero runtime dependencies)
  • Run: npm start
  • Tests: npm test
  • Unit tests only: npm run test:unit
  • Integration tests only: npm run test:integration
  • Coverage: npm run test:coverage
  • Type check: npm run typecheck

Commit Message Convention

This project uses semantic-release to automate versioning and publishing. All commit messages must follow the Conventional Commits format:

<type>: <description>

[optional body]

Types and their effect on versioning:

Type Version Bump When to use
feat: Minor (1.2.0 -> 1.3.0) New features or capabilities
fix: Patch (1.2.0 -> 1.2.1) Bug fixes
feat!: or fix!: Major (1.2.0 -> 2.0.0) Breaking changes (note the !)
chore: No release Maintenance, deps, config (not released)
docs: No release Documentation only
refactor: No release Code changes that don't fix bugs or add features
test: No release Adding or updating tests
ci: No release CI/CD changes

Important:

  • Use feat: or fix: when the change should trigger a new npm release
  • Use chore:, docs:, refactor:, test:, or ci: for changes that should NOT trigger a release
  • For breaking changes, add ! after the type (e.g., feat!: remove legacy API) or include BREAKING CHANGE: in the commit body

Release Process

Releases are fully automated via semantic-release on the main branch. When commits land on main:

  1. Commit messages are analyzed to determine the version bump
  2. CHANGELOG.md is updated automatically
  3. package.json version is updated
  4. Package is published to npm
  5. A GitHub release is created

Read the full file on GitHub · 55 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. 2mo ago First seen · 55 lines · 573 tokens per session scan A e14ad7c0a317

Subscribe to this mod's changes

git-watchtower CLAUDE.md is an instructions file published in the GitHub repository drummel/git-watchtower (11 stars, last pushed 13d ago), licensed MIT. It adds 573 tokens to every session, about $0.0023 per session on Opus 5.5. 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

git-watchtower CLAUDE.md compared with instructions from other repositories

git-watchtower CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git-watchtower CLAUDE.mddrummel/git-watchtowerInstructions file1113d agoMITA573Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode