Borrowing it
Nothing to install: this file belongs to dliedke/ClaudeCodeExtension. 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/dliedke/ClaudeCodeExtension/master/CLAUDE.mdgit clone --depth 1 https://github.com/dliedke/ClaudeCodeExtensionWrote 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/dliedke/claudecodeextension/claude-md)<a href="https://agentmods.dev/instructions/dliedke/claudecodeextension/claude-md"><img src="https://agentmods.dev/badge/instructions/dliedke/claudecodeextension/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.
<a href="https://agentmods.dev/instructions/dliedke/claudecodeextension/claude-md"><img src="https://agentmods.dev/badge/instructions/dliedke/claudecodeextension/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.07120 | $0.07120 |
| Opus 5.5 | $0.02848 | $0.02848 |
| Sonnet 5.5 | $0.01424 | $0.01424 |
| Haiku 4.5 | $0.00712 | $0.00712 |
Grade A, and why
ClaudeCodeExtension 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 today.
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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Claude Code Extension for Visual Studio
Project Overview
Visual Studio Extension (VSIX) for VS 2022/2026 — integrates AI code assistants (Claude Code, OpenAI Codex, Cursor Agent, Open Code, Devin, PI, Google Antigravity, Reasonix, Qwen Code, and Grok) via a native chat tab driven by each CLI's headless protocol ("native mode", default since v179.0) or an embedded terminal (Win32 SetParent interop).
- Author: Daniel Carvalho Liedke ([email protected]) | License: MIT
- Repository: https://github.com/dliedke/ClaudeCodeExtension
- Current Version: 275.0 | Target Framework: .NET Framework 4.7.2
Step-by-step procedures for recurring tasks (release, Exp-hive debugging, publish, adding a
provider/setting/UI file) live in docs/SKILLS.md. Short build/style brief for non-Claude agents: docs/AGENTS.md.
MANDATORY: Version & Documentation Updates
Every development session that modifies code MUST update before finishing:
Versioning scheme (since 11.0): each release bumps the MAJOR version by one — 22.0 → 23.0 → 24.0 and so on. Always use .0 as the minor (AssemblyVersion 24.0.0.0, manifest 24.0, README ### Version 24.0). Do not resume 10.x-style minor bumps.
Properties/AssemblyInfo.cs: BumpAssemblyVersionandAssemblyFileVersionsource.extension.vsixmanifest: BumpVersionin<Identity>tagREADME.md: Add### Version X.Yentry at top of## Version History- Style: Short, business-focused. One sentence per bullet (two max). Describe the user-visible feature or fix, not the implementation.
- Avoid: code/file/class/method names, internal selectors, file paths, constants, line numbers, JS snippets, framework jargon (
CoreWebView2,INPUT_RECORD,NavigationCompleted, etc.), step-by-step "how it works" explanations, and PR-description-style root-cause analysis. - Keep: what the user gets ("auto-confirms proxy block screens"), opt-in/opt-out status, and the menu/setting name they interact with.
- Technical details belong in commit messages and
docs/ARCHITECTURE.md, not in release notes. - Other README sections (Features, Supported AI Providers, System Requirements, Settings & Menus, etc.): Edits MUST be minimal. Update only the exact line/bullet affected by the change. Do not rewrite paragraphs, expand explanations, add subsections, reorder content, or restructure tables. If a new provider/setting needs a row, add one row. If a feature description needs a word change, change the word. README is reference doc — keep it slim to avoid file bloat.
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.
- today Changed f9bad05aecbe
- yesterday Changed df4c4d560708
- 2d ago Changed · +7 lines · +384 tokens per session 3ade0840fec7
- 3d ago Changed · +1 lines · +31 tokens per session 969c3d168ea1
- 4d ago Changed · +4 lines · +148 tokens per session 68a370abbe7d
- 5d ago Changed b6f00ad1f8e4
- 6d ago Changed eccd2df6ef69
- 7d ago Changed c539950be3eb
- 8d ago Changed · +2 lines · +151 tokens per session 0c1c205d99aa
- 9d ago First seen · 313 lines · 6,406 tokens per session scan A 76be8fa6c53f
ClaudeCodeExtension CLAUDE.md is an instructions file published in the GitHub repository dliedke/ClaudeCodeExtension (78 stars, last pushed yesterday), licensed MIT. It adds 7,120 tokens to every session, about $0.0285 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.