llm-safe-haven: Instructions file for Claude Code

CLAUDE.md

llm-safe-haven CLAUDE.md is an instructions file for Claude Code from pleasedodisturb/llm-safe-haven. It costs 1,322 tokens per session, scanned A, original, MIT.

Repository instructions for LLM Safe Haven, a security toolkit that helps individual developers protect setups where artificial-intelligence coding agents run automatically. They describe the project structure and require test-driven development, meaning behavior changes start with a failing test.

In plain words
What is it for?
Working on the command-line installer, agent plugins, safety hooks, secret manifests, security guides, and test-first behavior changes.
Why use it?
They make security changes deliberate and verifiable, while directing agents to the correct project contracts and hardening components.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is pleasedodisturb/llm-safe-haven's own configuration. It tells Claude Code how to work on llm-safe-haven 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 llm-safe-haven configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pleasedodisturb/llm-safe-haven. 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/pleasedodisturb/llm-safe-haven/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pleasedodisturb/llm-safe-haven

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 llm-safe-haven CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pleasedodisturb/llm-safe-haven/claude-md"><img src="https://agentmods.dev/badge/instructions/pleasedodisturb/llm-safe-haven/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,322 This file is loaded in full into every session.
When invoked 1,322 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01322 $0.01322
Opus 5 $0.00661 $0.00661
Sonnet 5 $0.00264 $0.00264
Haiku 4.5 $0.00132 $0.00132

Measured 10d ago against content hash d81d01d7caef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

llm-safe-haven CLAUDE.md scanned grade A 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 10d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Zero runtime dependencies. Only Node.js built-ins (fs, path, os, crypto, child_process).
CLAUDE.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Safe Haven

What This Is

Security toolkit and reference for solo developers running autonomous AI coding agents. npx llm-safe-haven installs hooks and hardens your setup in 60 seconds.

This file does not restate global rules — read ~/.claude/CLAUDE.md first.

For the cross-agent working contract and current project state (shipped version, active milestone, next work), see AGENTS.md.

Project Structure

bin/ — CLI entry point (npx llm-safe-haven) lib/ — CLI logic (detect, install, audit, scan) lib/agents/ — Modular agent plugins (one file per agent) hooks/ — PreToolUse/PostToolUse hooks (the product) manifests/ — Secret manifest format docs/ — Reference documentation (threat model, hardening guides) docs/hardening/ — Per-agent hardening guides (6 agents) docs/guides/ — Quick start, tutorials

TDD — Non-Negotiable (adopted 2026-08-17)

Every behaviour change starts with a failing test. Not "tests alongside". Not "tests before the PR". The test is written first, it is run, it FAILS, and that failure is recorded — then the code is written.

The contract

  1. RED first. Write the test. Run it. It must fail for the reason you intend — a test that fails with TypeError: x is not a function proves nothing; it must fail on the assertion.
  2. Commit the RED separately, prefixed test(G-NNNN):, before the implementation commit. On a squash-merged repo this branch history is the only surviving evidence the order was honoured.
  3. Paste the verbatim RED output into the implementation commit message. "Tests added" is not evidence; the failure text is.
  4. GREEN. Implement. The named test now passes and nothing else broke.

Clear pass/fail criteria — what "proper test" means here

A test that cannot fail is worse than no test, because it ships confidence. Before writing one, state in a comment what would make it fail. Then:

Read the full file on GitHub · 118 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. 10d ago First seen · 118 lines · 1,322 tokens per session scan A d81d01d7caef

Subscribe to this mod's changes

llm-safe-haven CLAUDE.md is an instructions file published in the GitHub repository pleasedodisturb/llm-safe-haven (5 stars, last pushed 3d ago), licensed MIT. It adds 1,322 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

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.

github/spec-kit · 7,104 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