Borrowing it
Nothing to install: this file belongs to konan-1947/claude_diff_view_vscode_extension. 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/konan-1947/claude_diff_view_vscode_extension/main/CLAUDE.mdgit clone --depth 1 https://github.com/konan-1947/claude_diff_view_vscode_extensionWrote 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/konan-1947/claude_diff_view_vscode_extension/claude-md)<a href="https://agentmods.dev/instructions/konan-1947/claude_diff_view_vscode_extension/claude-md"><img src="https://agentmods.dev/badge/instructions/konan-1947/claude_diff_view_vscode_extension/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/konan-1947/claude_diff_view_vscode_extension/claude-md"><img src="https://agentmods.dev/badge/instructions/konan-1947/claude_diff_view_vscode_extension/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 | $0.03462 | $0.03462 |
| Opus 5 | $0.01731 | $0.01731 |
| Sonnet 5 | $0.00692 | $0.00692 |
| Haiku 4.5 | $0.00346 | $0.00346 |
Grade B, and why
claude_diff_view_vscode_extension CLAUDE.md scanned grade B 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
There used to be a third, hook-based pipeline (`PreToolUse`/`PostToolUse` hooks written into `~/.claude/settings.json`); it was removed in favor of detecting every CLI — including Claude — uniformly through the workspace How it starts
The opening of the file, as written. The whole thing — 127 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.
What This Extension Does
AI CLI diff view is a VS Code extension for reviewing AI CLI file edits inside VS Code.
Best supported review workflows: Claude, Codex, and Qwen — all detected uniformly via the workspace watcher (no CLI-specific hooks). Built-in session launch (startSession) is Claude-only.
Commands
npm install
npm run compile # tsc -p ./ → out/ (main build / correctness check)
npm run watch # tsc -watch -p ./ (normal dev loop)
npx @vscode/vsce package
- Press
F5to launch the Extension Development Host (.vscode/launch.json), and reload the host after each recompile. - There is no lint, formatter, or test runner configured.
npm run compileis the minimum correctness gate. Manually validate diff rendering, accept/revert, and navigation against the sample files incode_to_test/. node-ptyis a native module. If the integrated terminal fails to load (ABI mismatch against VS Code's Electron), rebuild it with the@electron/rebuilddevDependency. There is no postinstall script wiring this up.- Monaco and xterm assets are consumed directly from
node_modules/at runtime (loaded into webviews vialocalResourceRoots); there is no separate asset bundling step. - Strict TypeScript (
tsconfig.json:strict: true, CommonJS, ES2020 target). 2-space indentation, semicolons, single quotes;PascalCasefor classes/providers,camelCasefor functions/variables,kebab-casefor asset filenames.
Architecture
Runtime shape
src/extension.ts is the entry point, activated onStartupFinished. It wires together the DiffManager, the workspace and git-branch watchers, the Monaco diff custom-editor provider, the navigation manager, and both webview surfaces (terminal + nav bar), then registers commands.
The core responsibility: capture a before-image of a file, detect the after-image once an AI tool writes it, then present a reviewable Monaco diff while keeping enough per-file state to accept or reject individual hunks.
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.
- 4d ago Changed · +1 lines · +63 tokens per session d80e0206bd01
- 9d ago First seen · 126 lines · 3,399 tokens per session scan B 55b3cf92a2c9
claude_diff_view_vscode_extension CLAUDE.md is an instructions file published in the GitHub repository konan-1947/claude_diff_view_vscode_extension (5 stars, last pushed 6d ago), licensed MIT. It adds 3,462 tokens to every session, about $0.0173 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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.