What is claude-ext CLAUDE.md?

Instruction notes for claude-ext, a framework that extends the Claude Code command-line tool with reusable components called extensions. They describe its structure, design rules, built-in templates, and how to add an extension.

Understanding the project layout, following its extension rules, using its templates, and building or maintaining new extensions.

They give contributors a shared reference for changing the framework without breaking its separation between core code and extensions.

How claudebot101001/claude-ext configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to claudebot101001/claude-ext. 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/claudebot101001/claude-ext/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/claudebot101001/claude-ext

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/claudebot101001/claude-ext/claude-md/github.svg)](https://agentmods.dev/instructions/claudebot101001/claude-ext/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/claudebot101001/claude-ext/claude-md"><img src="https://agentmods.dev/badge/instructions/claudebot101001/claude-ext/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/claudebot101001/claude-ext/claude-md"><img src="https://agentmods.dev/badge/instructions/claudebot101001/claude-ext/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 477 This file is loaded in full into every session.

When invoked 477 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00477	$0.00477
Opus 5	$0.00238	$0.00238
Sonnet 5	$0.00095	$0.00095
Haiku 4.5	$0.00048	$0.00048

Measured 8d ago against content hash a08673bfea34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-ext 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.

CLAUDE.md · 43 lines

What it actually says

claude-ext

Extensible framework for Claude Code CLI. Wraps CLI invocations + manages extension lifecycles.

Deep implementation reference: docs/ARCHITECTURE.md.

Quick Reference

claude-ext/
├── core/               # Stable layer: engine, sessions, bridge, templates, registry
│   ├── templates/      # Built-in YAML + MD template files (coder, reviewer, researcher)
│   └── *.py            # Core modules (never import extensions)
├── extensions/         # Each subdirectory is a self-contained extension
│   └── <ext>/
│       ├── extension.py      # ExtensionImpl(Extension) — entry point
│       ├── mcp_server.py     # MCP stdio server (optional)
│       └── templates/        # Extension-owned YAML + MD templates (optional)
├── config.yaml         # Runtime config (.gitignored, contains secrets)
├── config.yaml.example # Config template with all options documented
└── main.py             # Entry point

Pre-commit: Always ruff format <file> before commit.

Design Principles

Core never imports any extension. Discovery via importlib only.
Extensions never import each other. Use dependencies + engine.services for runtime access.
Each extension is self-contained. Delete directory + remove from enabled = zero impact.
New features = new directories. Modifying core/ or other extensions = abstraction leak.
MCP access is fail-closed. Templates use allowlists. New extensions auto-excluded from restricted templates.

Adding a New Extension

Create extensions/<name>/extension.py with ExtensionImpl(Extension)
Implement start() and stop()
Add to enabled list in config.yaml
(Optional) Add MCP server: create mcp_server.py subclassing MCPServerBase, register in start()
(Optional) Add templates: create templates/*.yaml + .md files, register in start()

No core changes, no other extension changes required.

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.

8d ago First seen · 43 lines · 477 tokens per session scan A a08673bfea34

Subscribe to this mod's changes

claude-ext CLAUDE.md is an instructions file published in the GitHub repository claudebot101001/claude-ext (2 stars, last pushed 5mo ago), licensed MIT. It adds 477 tokens to every session, about $0.0024 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.

Building agents

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

claude-ext: Instructions file for Claude Code