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/kodroi/block/claude-mdgit clone --depth 1 https://github.com/kodroi/blockWhat 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 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
block 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This plugin provides file and directory protection using .block configuration files. It supports both Claude Code and OpenCode. When installed, the plugin intercepts file modification operations and blocks them based on protection rules.
Architecture
The core protection logic lives in hooks/protect_directories.py (Python, no external dependencies). Both Claude Code and OpenCode integrations call this script.
Claude Code integration
- PreToolUse hook: Runs
protect_directories.pyto check if the target file is protected before allowing Edit, Write, NotebookEdit, or Bash operations hooks/hooks.json- Hook configurationhooks/run-hook.cmd- Cross-platform entry point (polyglot script)commands/create.md- Interactive command for creating.blockfiles.claude-plugin/plugin.json- Plugin metadata
OpenCode integration
- tool.execute.before hook: TypeScript plugin that calls
protect_directories.pybefore edit, write, bash, or patch operations opencode/index.ts- Plugin entry pointopencode/package.json- npm package metadata
Dependencies
- Python 3.8+ - Required for the protection hook (no external packages needed)
- pytest - For running tests (dev dependency only)
Testing
Run the test suite with pytest:
# Install dev dependencies
pip install -e ".[dev]"
# Run all tests
pytest tests/ -v
# Run specific test file
pytest tests/test_basic_protection.py -v
# Run with coverage
pytest tests/ -v --cov=hooks --cov-report=term-missing
Testing the Plugin Locally
To test protection locally:
- Ensure Python 3.8+ is installed
- Create a test directory with a
.blockfile - Attempt to modify files in that directory - operations should be blocked
Git Worktrees
When creating git worktrees, use the .worktree folder in the project root:
git worktree add .worktree/<worktree-name> <branch-name>
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 · 65 lines · 535 tokens per session scan A 8eca6a6b8057
block CLAUDE.md is an instructions file published in the GitHub repository kodroi/block (2 stars, last pushed 6mo ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 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 2026-08-31.
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.