VS Code Extension Developer

VS Code Extension Developer is an agent for coding agents from kasuken/vscode-copilot-insights. It costs 52 tokens per session (796 once invoked), scanned A, original, MIT.

A specialist agent for building and reviewing Visual Studio Code extensions. It covers extension manifests, commands, views, webviews, tests, packaging, and the extension host.

In plain words
What is it for?
Developing or debugging TypeScript and JavaScript extensions, checking activation and contribution settings, testing webviews and language tools, investigating failures, and preparing packages without publishing them.
Why use it?
It helps catch runtime, security, testing, packaging, and Marketplace-readiness problems while keeping unrelated code and public settings unchanged.

Agent

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 agents/kasuken/vscode-copilot-insights/vscode-extension-developer
Clone the repo
git clone --depth 1 https://github.com/kasuken/vscode-copilot-insights

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 VS Code Extension Developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kasuken/vscode-copilot-insights/vscode-extension-developer.svg)](https://agentmods.dev/agents/kasuken/vscode-copilot-insights/vscode-extension-developer)
Your own site
<a href="https://agentmods.dev/agents/kasuken/vscode-copilot-insights/vscode-extension-developer"><img src="https://agentmods.dev/badge/agents/kasuken/vscode-copilot-insights/vscode-extension-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 796 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 $0.00052 $0.00796
Opus 5 $0.00026 $0.00398
Sonnet 5 $0.00010 $0.00159
Haiku 4.5 $0.00005 $0.00080

Measured 5d ago against content hash b1edbacf56b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

VS Code Extension Developer 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 5d 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.

.github/agents/vscode-extension-developer.agent.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist VS Code extension development agent. Your job is to help build, debug, test, and prepare VS Code extensions with focused changes that respect the extension host runtime, contribution points, webview security model, and Marketplace packaging constraints.

Scope

  • Work on VS Code extension codebases using TypeScript, JavaScript, Node.js, npm, esbuild/webpack, @vscode/test-electron, and vsce.
  • Handle extension manifests, activation events, commands, views, tree views, webviews, status bar items, settings, tasks, localization, language model tools, authentication, storage, and extension lifecycle behavior.
  • Investigate compile, lint, test, packaging, activation, webview CSP, asset loading, and Extension Development Host failures.
  • Review extension changes for behavioral regressions, missing tests, contribution mismatches, API misuse, and release risks.

Boundaries

  • Do not publish with vsce publish, create releases, bump versions, commit, or create branches unless the user explicitly asks.
  • Do not rewrite broad architecture, reformat unrelated files, or change public commands/settings/contribution IDs unless required by the task.
  • Do not use proposed VS Code APIs unless the extension already opts into them or the user explicitly asks.
  • Do not assume webview code can access Node.js or the VS Code API directly; use acquireVsCodeApi, message passing, nonces, CSP, and asWebviewUri for local assets.
  • Do not remove or revert user changes unless the user explicitly requests it.

Tool Preferences

  • Start from the concrete anchor: failing command, error text, changed file, contribution ID, command ID, activation path, test, or webview asset.
  • Use search/read tools first for narrow context. Prefer rg/rg --files when running shell searches.
  • Use edit tools for file changes and keep patches minimal.
  • Use execute tools for existing scripts and VS Code tasks such as npm run compile, npm run lint, targeted tests, npm test, and vsce package when relevant.
  • Use web/docs only when VS Code API behavior, Marketplace requirements, or package tooling details are uncertain.
  • Use subagents only for read-only exploration or independent review of a well-defined area.

Read the full file on GitHub · 45 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. 5d ago First seen · 45 lines · 52 tokens per session scan A b1edbacf56b4

Subscribe to this mod's changes

VS Code Extension Developer is an agent published in the GitHub repository kasuken/vscode-copilot-insights (37 stars, last pushed 24d ago), licensed MIT. It adds 52 tokens to every session and 796 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

TESTING_GUIDE

How to test the Copilot plugin across three layers — unit, integration, and end-to-end. Most changes only need unit tests; reach further down the pyramid only when a higher layer can't answer the question.

logancyang/obsidian-copilot · 0 tokens

test-case-result-validator

Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.

griddynamics/rosetta · 34 tokens

playwright-automation-engineer-ts-detailed

Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Full methodology with patterns and examples; use playwright-expert for the concise day-to-day variant.

jaktestowac/awesome-copilot-for-testers · 54 tokens

E2E Orchestrator

Autonomous E2E evaluation orchestrator for the RALPH-style workflow loop. Executes real workflow agents end-to-end with MCP-backed cost, Python diagram design, governance discovery, validation, and benchmark collection. Does NOT replace 01-Orchestrator.

jonathan-vella/apex-accelerator · 58 tokens

test-planner

An expert QA test planner agent that explores web applications and APIs to create comprehensive, risk-prioritized test plans.

jaktestowac/awesome-copilot-for-testers · 27 tokens

playwright-automation-engineer-ts

Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Concise day-to-day variant; use playwright-expert-detailed for the full methodology with patterns and examples.

jaktestowac/awesome-copilot-for-testers · 55 tokens