Visual Studio Code is a code editor that supports editing, navigating, understanding, debugging, and extending software projects. Developers use it for the edit-build-debug cycle, and the catalogue add-ons provide skills, instructions, and agents for working within the editor.
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.
npx skills add microsoft/vscode --skill generate-run-commandsgit clone --depth 1 https://github.com/microsoft/vscodeWrote 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/skills/microsoft/vscode/generate-run-commands)<a href="https://agentmods.dev/skills/microsoft/vscode/generate-run-commands"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/generate-run-commands/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/skills/microsoft/vscode/generate-run-commands"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/generate-run-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00036 | $0.00569 |
| Opus 5.5 | $0.00014 | $0.00228 |
| Sonnet 5.5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
generate-run-commands 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Run Commands
Help the user set up run commands for the current Agent Session workspace. Run commands appear in the session's Run button in the title bar.
Understanding the task schema
A run command is a tasks.json task with:
"inAgents": true— required: makes the task appear in the Agents run button"runOptions": { "runOn": "worktreeCreated" }— optional: auto-runs the task whenever a new worktree is created (use for setup/install commands)
{
"tasks": [
{
"label": "Install dependencies",
"type": "shell",
"command": "npm install",
"inAgents": true,
"runOptions": { "runOn": "worktreeCreated" }
},
{
"label": "Start dev server",
"type": "shell",
"command": "npm run dev",
"inAgents": true
}
]
}
Decision logic
First, read the existing .vscode/tasks.json to check for existing run commands (inAgents: true tasks).
If run commands already exist: treat this as a modify request — ask the user what they'd like to change (add, remove, or update a command).
If no run commands exist: try to infer the right commands from the workspace:
- Check
package.json,Makefile,pyproject.toml,Cargo.toml,go.mod,.nvmrc, or other project files to understand the stack and common commands. - If it's clear what the setup command is (e.g.,
npm install,pip install -r requirements.txt), add it with"runOptions": { "runOn": "worktreeCreated" }— no need to ask. - If it's clear what the primary run/dev command is (e.g.,
npm run dev,cargo run), add it with just"inAgents": true. - Only ask the user if the commands are ambiguous (e.g., multiple equally valid options, no recognizable project structure, or the project uses a non-standard setup).
Writing the file
Always write to .vscode/tasks.json in the workspace root. If the file already exists, merge — do not overwrite unrelated tasks.
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.
- 1mo ago First seen · 54 lines · 36 tokens per session scan A 3a783d08b42e
generate-run-commands is a skill published in the GitHub repository microsoft/vscode (194,166 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 569 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and workflowbuildercreatetasks silence rules. Load whenever any of these tags appear or after calling workflowbuildercreatetasks.
om-build-workflow
Build or extend standalone business workflows, activities, event triggers, durable user tasks, compensation, output paths, idempotency, and live progress. Use for "add workflow", "custom activity", "CALLAPI", "approval task", "workflow progress", or "zbuduj workflow".
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.
output-dev-code-style
Code style conventions for Output SDK workflow projects. Use when writing or reviewing any TypeScript/JavaScript code. Discovers the project's own linting rules first; falls back to Output SDK conventions when no linter is configured.
output-dev-llm-streaming
Implement LLM text streaming in Output workflow steps with generateTextWithStreaming, Agent.generateWithStreaming, streamText, or Agent.stream. Use when adding token progress, onChunk callbacks, or handling streamText onEnd/onError with Temporal retries.
output-dev-workflow-cost
Calculate and display the cost of an Output SDK workflow execution run. Use when checking LLM token costs, API service costs, or total spend for a specific workflow run.