Borrowing it
Nothing to install: this file belongs to kasuken/vscode-copilot-insights. 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/kasuken/vscode-copilot-insights/main/.github/agents/vscode-extension-developer.agent.mdgit clone --depth 1 https://github.com/kasuken/vscode-copilot-insightsWrote 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/agents/kasuken/vscode-copilot-insights/vscode-extension-developer)<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/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/agents/kasuken/vscode-copilot-insights/vscode-extension-developer"><img src="https://agentmods.dev/badge/agents/kasuken/vscode-copilot-insights/vscode-extension-developer.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 | $0.00052 | $0.00796 |
| Opus 5.5 | $0.00021 | $0.00318 |
| Sonnet 5.5 | $0.00010 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00080 |
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 2mo 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 — 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, andvsce. - 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, andasWebviewUrifor 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 --fileswhen 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, andvsce packagewhen 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.
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.
- 2mo ago First seen · 45 lines · 52 tokens per session scan A b1edbacf56b4
VS Code Extension Developer is an agent published in the GitHub repository kasuken/vscode-copilot-insights (38 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 796 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
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.
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.
test-planner
An expert QA test planner agent that explores web applications and APIs to create comprehensive, risk-prioritized test plans.
ui-test-automation
This custom agent creates and maintains Playwright tests for UI automation.
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.
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.