Borrowing it
Nothing to install: this file belongs to gugastork/watchtower-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gugastork/watchtower-ai/main/CLAUDE.mdgit clone --depth 1 https://github.com/gugastork/watchtower-aiWrote 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/gugastork/watchtower-ai/claude-md)<a href="https://agentmods.dev/instructions/gugastork/watchtower-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/gugastork/watchtower-ai/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 5.1 | $0.00349 | $0.00349 |
| Opus 5 | $0.00175 | $0.00175 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
watchtower-ai 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 8d 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
Instructions for AI assistants working on this repository.
About This Repository
This is the knowledge layer of the WatchTower builders community. It contains prompts, workflows, tools, templates, case studies, summaries and curated resources about practical AI applications.
Content Standards
- All content must be tested and real-world — no theoretical or untested material
- Every file must follow the content template from
templates/content-templates/ - Contributions must include context: what it does, when to use it, limitations
- No AI-generated content that has not been reviewed and validated by a human
Repository Structure
prompts/ → tested prompts (subdirs: claude-code, agents, research, marketing)
workflows/ → AI workflows (subdirs: claude-code, cursor, n8n, automations)
tools/ → plugins, CLI tools, open source utilities
templates/ → reusable project templates + content templates
case-studies/ → real experiments with results
summaries/ → distilled insights from papers, tutorials, discussions
resources/ → curated books, repos, articles
Writing Style
- Use English for all content
- Be direct and practical — no filler text
- Use Markdown for all files
- File names: lowercase with hyphens (e.g.
code-review-with-context.md)
When Helping Contributors
- Point them to the correct content template in
templates/content-templates/ - Remind them to check CONTRIBUTING.md for quality standards
- Suggest the correct directory and subdirectory for their content
- Help them structure content clearly but do not generate fake examples or untested content
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.
- 8d ago First seen · 41 lines · 349 tokens per session scan A 6a5ef401476e
watchtower-ai CLAUDE.md is an instructions file published in the GitHub repository gugastork/watchtower-ai (24 stars, last pushed 1mo ago), licensed MIT. It adds 349 tokens to every session, about $0.0017 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
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.
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.
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).
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).
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.
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.