agentleFS
KUNDURUHIMANEESHREDDYKUNDURUHIMANEESHREDDY/saber/.agents/skills/generate-run-commands/SKILL.md

generate-run-commands

Skill0 starsChanged 57 days agoMITView on GitHub

Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

  • Installs packages

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    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).

    line 41
  2. Very specific:

    Check package.json, Makefile, pyproject.toml, Cargo.toml, go.mod, .nvmrc, or other project files to understand the stack and common …

    line 44
  3. Very specific:

    If it's clear what the setup command is (e.g., npm install, pip install -r requirements.txt), add it with "runOptions": { "runOn": …

    line 45
  4. Very specific:

    If it's clear what the primary run/dev command is (e.g., npm run dev, cargo run), add it with just "inAgents": true.

    line 46
  5. Distinctive:

    Only ask the user: if the commands are ambiguous (e.g., multiple equally valid options, no recognizable project structure, or the project …

    line 47
  6. Very specific:

    Always write to .vscode/tasks.json in the workspace root.

    line 51
  7. Distinctive:

    After writing, briefly confirm what was added and how to trigger it from the Run button.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Customize this skill and select save to override its behavior. Delete that copy to restore the built-in behavior. -->

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.

After writing, briefly confirm what was added and how to trigger it from the Run button.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.