setup

Setup instructions for diagnosing and fixing the connection between an AI coding agent and Visual Studio Code. They cover the active window, extension, Node.js, and connection settings.

In plain words
What is it for?
Use them to check the bridge, install the required VS Code extension, verify Node.js, and choose the correct project window.
Why use it?
They help identify why the VS Code bridge is missing, failing, or connected to the wrong window.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mend3/vscode-agent-bridge/setup
Any agent
npx skills add mend3/vscode-agent-bridge --skill setup
Clone the repo
git clone --depth 1 https://github.com/mend3/vscode-agent-bridge

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00436
Opus 5 $0.00015 $0.00218
Sonnet 5 $0.00006 $0.00087
Haiku 4.5 $0.00003 $0.00044

Measured yesterday against content hash 3d6864b2a808, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

packages/plugin/skills/setup/SKILL.md · 62 lines

What it actually says

Bridge setup

Work through these in order and stop at the first one that fails.

1. Is a window serving this project?

node "${CLAUDE_PLUGIN_ROOT}/bin/bridge-doctor.mjs" "${CLAUDE_PROJECT_DIR}"

It prints the registry, every live window, which one this directory resolves to and a health check. Read its output before changing anything.

2. Is the extension installed?

code --list-extensions | grep -i agent-bridge

If it is missing:

code --install-extension vscode-agent-bridge.vscode-agent-bridge

Then reload the VS Code window. Confirm the status bar shows ⇄ Bridge :<port>.

3. Does this machine have Node?

node --version

The connection runs through a small Node script. If Node is absent, VS Code's own runtime can run it — the path is recorded as runtime in the instance file that bridge-doctor prints. Point the MCP server at that binary with ELECTRON_RUN_AS_NODE=1 set.

4. Wrong window, or several candidates

The bridge refuses to guess when more than one window could serve the directory. Either close the window you do not want, or name one explicitly:

export BRIDGE_URL=http://127.0.0.1:<port>/mcp
export BRIDGE_TOKEN=<token from the instance file>

5. Edits are refused

write_denied means the workspace has writes disabled. In VS Code, set agentBridge.writeMode to confirm (ask each time) or auto (apply without asking).

Reporting back

Tell the user which step failed and what to do about it. Do not retry a failing connection more than twice.

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. yesterday First seen · 62 lines · 31 tokens per session scan A 3d6864b2a808

Subscribe to this mod's changes

setup is a skill published in the GitHub repository mend3/vscode-agent-bridge (0 stars, last pushed 21d ago), licensed MIT. It adds 31 tokens to every session and 436 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens