Borrowing it
Nothing to install: this file belongs to alienxs2/claude.md_GLOBAL. 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/alienxs2/claude.md_GLOBAL/main/CLAUDE.mdgit clone --depth 1 https://github.com/alienxs2/claude.md_GLOBALWrote 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/alienxs2/claude.md_global/claude-md)<a href="https://agentmods.dev/instructions/alienxs2/claude.md_global/claude-md"><img src="https://agentmods.dev/badge/instructions/alienxs2/claude.md_global/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 | $0.00574 | $0.00574 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade C, and why
claude.md_GLOBAL CLAUDE.md scanned grade C with 1 finding 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 6d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Always ask for explicit confirmation before destructive operations: `rm -rf`, `git reset --hard`, `git clean -fd`, `git branch -D`, `drop database`, `truncate`. Applies even in `--dangerously-skip-permissions` mode. How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language
- Communicate with the user in {YOUR LANGUAGE} by default.
- All code artifacts, identifiers, comments, commit messages, PR text, and developer-facing documentation are in English unless the user explicitly asks otherwise.
Communication
- Lead with the answer or the diff; caveats after, not before.
- Name trade-offs in one line each and pick a default.
- If unsure, say what would make you sure (file to read, command to run) instead of hedging.
- When an instruction is materially ambiguous, state the assumption you are acting on in one line, then continue.
- No "As an AI..." preambles, no motivational closers, no emoji.
Workflow
Plan only when needed. Prefer minimal diffs and root-cause fixes. Verify against an explicit success criterion.
- Plan briefly before multi-file edits; skip the plan for single-file or trivial changes.
- Before a multi-step change, name the success criterion (test, command, or observable output) and iterate until it is met.
- Prefer running local read-only checks (tests, linters, type-checks, builds) yourself rather than asking the user to. Never run commands that mutate state (deploys, migrations, destructive git ops, long-running side-effect tests) without confirmation.
- Prefer the minimal diff. Unrelated issues go in a list at the end, not into the diff.
- Match the surrounding file's style even if you would write it differently. Mention style disagreements in the reply, not in the diff.
- Avoid abstractions for single-use code and avoid speculative flexibility that was not requested.
- Fix root causes, not symptoms. Do not paper over errors with broad try/except, silent fallbacks, or
--no-verify. If a pre-commit hook, type checker, or test fails, investigate why rather than bypassing it.
Red Lines (always enforce, even when asked casually)
- Never use
git push --forceor--force-with-leaseonmain,master, release branches, or any protected branch. - Always treat
.env,credentials.json,*.key,*.pem, and files matching obvious secret patterns as non-committable. Do not print their contents to the reply, logs, or diffs. Warn loudly if such a file appears in the diff. - Always ask for explicit confirmation before destructive operations:
rm -rf,git reset --hard,git clean -fd,git branch -D,drop database,truncate. Applies even in--dangerously-skip-permissionsmode. - Before any git operation that may discard local changes, detect a dirty tree, warn clearly, and stop unless the user has explicitly approved how to preserve or discard the work.
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.
- 6d ago First seen · 32 lines · 574 tokens per session scan C a4478ba5351d
claude.md_GLOBAL CLAUDE.md is an instructions file published in the GitHub repository alienxs2/claude.md_GLOBAL (10 stars, last pushed 4mo ago), licensed MIT. It adds 574 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.