Borrowing it
Nothing to install: this file belongs to edwardyen724-g/david-vscode. 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/edwardyen724-g/david-vscode/main/CLAUDE.mdgit clone --depth 1 https://github.com/edwardyen724-g/david-vscodeWrote 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/edwardyen724-g/david-vscode/claude-md)<a href="https://agentmods.dev/instructions/edwardyen724-g/david-vscode/claude-md"><img src="https://agentmods.dev/badge/instructions/edwardyen724-g/david-vscode/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/edwardyen724-g/david-vscode/claude-md"><img src="https://agentmods.dev/badge/instructions/edwardyen724-g/david-vscode/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 | $0.02524 | $0.02524 |
| Opus 5 | $0.01262 | $0.01262 |
| Sonnet 5 | $0.00505 | $0.00505 |
| Haiku 4.5 | $0.00252 | $0.00252 |
Grade A, and why
david-vscode 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 9d 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 — 129 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: David — agent orchestration for Claude Code
A VS Code extension that runs multiple specialist claude subprocesses (one per agent) on a single project, coordinated by a planner+workers overseer. Provides scheduled jobs, a nightly memory-distillation dream cycle, a skills system, and portable agent templates.
Status (as of 2026-05-23): v0.1.0-rc1 is built. david-0.1.0-rc1.vsix is the most recent package. The current focus is shipping v0.1 to the VS Code Marketplace / Open VSX, then building v0.2+. Marketing is a separate effort.
Build, package, install
npm install # one-time
npm run compile # tsc -p . → out/
npm run watch # tsc -watch for active dev
npx tsc --noEmit -p . # typecheck-only
# Produce a .vsix:
npx @vscode/vsce package --allow-missing-repository --skip-license
# Local install:
code --install-extension ./david-<version>.vsix
# Publish (when Edward signs off — irreversible, public):
npx @vscode/vsce login edwardyen724 # one-time
npx @vscode/vsce publish # uses package.json version
# or:
npx ovsx publish david-<version>.vsix -p <openvsx-token>
Manual debug: open this folder in VS Code, press F5 → "Run David (mock)" — boots an Extension Development Host with the mock seed. No real claude subprocess spawns unless you register a real folder via the welcome view.
No automated tests exist. v0.1 shipped on manual click-through QA + real-workspace smoke tests. If you propose adding tests, surface that as a real architectural choice (test runner, mocking strategy for node-pty/claude) — don't drop a vitest/jest scaffold unprompted.
Architecture — the non-obvious bits
The plugin is mostly a UI + spawner over a file-bus. All cross-agent state lives in ~/.david/workspaces/<slug>/. Re-spawning rehydrates from disk.
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.
- 9d ago First seen · 129 lines · 2,524 tokens per session scan A 88a6c75efb89
david-vscode CLAUDE.md is an instructions file published in the GitHub repository edwardyen724-g/david-vscode (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,524 tokens to every session, about $0.0126 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
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.