knowledge-interaction-surfaces-vscode-bridge

knowledge-interaction-surfaces-vscode-bridge is a skill for Claude Code, Codex from echoVic/blade-code. It costs 155 tokens per session (1,508 once invoked), scanned A, original, MIT.

A codebase guide for the VS Code extension that connects the command-line agent to the editor through a small WebSocket message service.

In plain words
What is it for?
Use it for extension startup, port discovery, editor commands, file and diff operations, diagnostics, status indicators, or VSIX packaging.
Why use it?
It helps developers modify editor integration without confusing this custom connection with ACP, a separate agent communication standard.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for extension startup, port discovery, editor commands, file and diff operations, diagnostics, status indicators, or VSIX packaging.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/echovic/blade-code/vscode-bridge
Install

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.

Any agent
npx skills add echoVic/blade-code --skill vscode-bridge
Clone the repo
git clone --depth 1 https://github.com/echoVic/blade-code

Made for: Claude Code, Codex.

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.

agentmods badge for knowledge-interaction-surfaces-vscode-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/echovic/blade-code/vscode-bridge.svg)](https://agentmods.dev/skills/echovic/blade-code/vscode-bridge)
Your own site
<a href="https://agentmods.dev/skills/echovic/blade-code/vscode-bridge"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/vscode-bridge.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,508 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00155 $0.01508
Opus 5 $0.00077 $0.00754
Sonnet 5 $0.00031 $0.00302
Haiku 4.5 $0.00015 $0.00151

Measured 4d ago against content hash 95951cc0a4e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

knowledge-interaction-surfaces-vscode-bridge 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 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.

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.

.trae/knowledges/interaction-surfaces/vscode-bridge/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Module Structure

VS Code 扩展是独立于 ACP 的轻量编辑器桥:扩展进程启动 WebSocket server,CLI 通过环境 变量或端口文件发现它,RPC 直接调用 VS Code API。

Directory Layout

  • packages/vscode/src/extension.ts — 扩展激活、WebSocket 生命周期与全部 RPC handler
  • packages/vscode/package.json — 激活事件、命令、设置、构建和打包入口
  • packages/vscode/README.md — 当前公开 RPC 和安装方式
  • packages/vscode/TODO.md — 已知稳定性缺口与后续能力边界
  • packages/cli/src/slash-commands/ide.ts — CLI 端口发现、连接探测和安装提示
  • packages/cli/src/ide/ — IDE 环境检测与扩展安装命令

Key Entry Points

  • activate() in packages/vscode/src/extension.ts — 注册 start/stop/status 并按配置自动启动
  • startServer() in packages/vscode/src/extension.ts — 建立 WebSocket、写端口文件和终端环境配置
  • handleMessage() in packages/vscode/src/extension.ts — RPC method 分派
  • handleConnect() in packages/cli/src/slash-commands/ide.ts — CLI 侧发现并探测扩展端口

Gotchas

  • VS Code 桥不是 ACP:它使用自定义 WebSocket {id, method, params} 协议,不能把 ACP Session 方法或能力协商假设套到该连接 (packages/vscode/src/extension.ts, packages/cli/src/acp/index.ts)
  • /ide connect 只建立一次 WebSocket 探测后立即关闭,却把模块级状态记为 connected;该状态不是持久连接健康度,也不会驱动后续 RPC (packages/cli/src/slash-commands/ide.ts)
  • 当前 CLI 只实现端口发现和连接探测,仓库中没有消费 openFileopenDiff、selection 或 diagnostics RPC 的长连接客户端;扩展公开能力不能等同于 Agent 已接入能力 (packages/cli/src/slash-commands/ide.ts, packages/vscode/src/extension.ts)
  • 端口发现先读 BLADE_IDE_PORT,再读单一 ~/.blade/ide-port;多窗口会覆盖同一文件,CLI 也不会按 workspace 选择实例 (packages/cli/src/slash-commands/ide.ts, packages/vscode/src/extension.ts, packages/vscode/TODO.md)
  • WebSocket server 未配置 host、认证或 origin 校验,消息参数使用 any 且无 schema;在扩大功能或网络暴露前必须先补协议校验与访问边界 (packages/vscode/src/extension.ts, packages/vscode/TODO.md)
  • openFile.options.line 是 1-based 并在调用 VS Code API 前减一,而 selection/diagnostic 返回值是 VS Code 原生 0-based;调用方不能混用坐标系 (packages/vscode/src/extension.ts)
  • setTerminalEnv() 更新的是 Workspace 级集成终端配置且异步 Promise 未等待,只影响之后创建的终端;当前终端仍依赖扩展进程环境或端口文件 (packages/vscode/src/extension.ts)
  • stopServer() 删除全局端口文件但不验证其中 pid/port 是否仍属于当前窗口;这与单文件多窗口限制是同一个生命周期风险 (packages/vscode/src/extension.ts, packages/vscode/TODO.md)

Read the full file on GitHub · 58 lines

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.

  1. 4d ago First seen · 58 lines · 155 tokens per session scan A 95951cc0a4e1

Subscribe to this mod's changes

knowledge-interaction-surfaces-vscode-bridge is a skill published in the GitHub repository echoVic/blade-code (178 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session and 1,508 once invoked, about $0.0008 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 2026-09-03.

Related

Other skills, from other repositories

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

alleneee/skill-agent · 35 tokens

artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

alleneee/skill-agent · 63 tokens

claude-design

Design one-off HTML artifacts (landing, deck, prototype).

StarryCod/cogitum · 16 tokens

pretext

Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.

StarryCod/cogitum · 56 tokens

html-artifacts

Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.

langchain-ai/open-swe · 51 tokens

langbot-dev

Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…

langbot-app/LangBot · 136 tokens