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/drummel/git-watchtower/claude-mdgit clone --depth 1 https://github.com/drummel/git-watchtowerWhat 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 | $0.00573 | $0.00573 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
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 2d 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.
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.watchfor 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:orfix:when the change should trigger a new npm release - Use
chore:,docs:,refactor:,test:, orci:for changes that should NOT trigger a release - For breaking changes, add
!after the type (e.g.,feat!: remove legacy API) or includeBREAKING CHANGE:in the commit body
Release Process
Releases are fully automated via semantic-release on the main branch. When commits land on main:
- Commit messages are analyzed to determine the version bump
CHANGELOG.mdis updated automaticallypackage.jsonversion is updated- Package is published to npm
- A GitHub release is created
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.
- 2d ago First seen · 55 lines · 573 tokens per session scan A e14ad7c0a317
git-watchtower CLAUDE.md is an instructions file published in the GitHub repository drummel/git-watchtower (11 stars, last pushed 4d ago), licensed MIT. It adds 573 tokens to every session, about $0.0029 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.