agentleFS
reefbarmanreefbarman/agentlink/.agents/skills/agentlink-dogfood-install/SKILL.md

agentlink-dogfood-install

Skill2 starsChanged 21 days agoMITView on GitHub

Install AgentLink; wait for reload.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this workflow when a task needs the current AgentLink checkout installed into VS Code for live testing.

    line 8
  2. Very specific:

    Run npm run release -- --install from the repository root with execute_command using sandbox_permissions: "require_escalated" and a clear …

    line 13
  3. Distinctive:

    Do not retry the install in the sandbox.

    line 14
  4. Distinctive:

    After a successful install, stop all implementation, testing, terminal work, and smoke testing.

    line 15
  5. Distinctive:

    Do not assume installation activates the new extension in the current window.

    line 17
  6. Distinctive:

    Use concise wording such as:

    line 30
  7. Distinctive:

    Do not call additional tools after issuing this handoff until the user confirms reload.

    line 34

≈ “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

AgentLink Dogfood Install

Use this workflow when a task needs the current AgentLink checkout installed into VS Code for live testing.

Required workflow

  1. Finish the intended code and documentation changes and run the appropriate validation before installing.
  2. Run npm run release -- --install from the repository root with execute_command using sandbox_permissions: "require_escalated" and a clear reason. The install must run outside the sandbox because sandboxed installation does not update the real VS Code extension installation.
  3. Do not retry the install in the sandbox. If the escalated command is rejected or fails, report the exact result and stop unless the returned retry guidance authorizes a different exact recovery.
  4. After a successful install, stop all implementation, testing, terminal work, and smoke testing. Ask the user to reload the relevant VS Code window or windows and tell you when reload is complete.
  5. End the turn with set_task_status using status: "waiting_for_user". Include the installed version when known, and provide a continuation action that asks the user to confirm the reload.
  6. Do not assume installation activates the new extension in the current window. Do not continue merely because the install command succeeded or because VS Code reports an update badge.
  7. Resume live smoke testing only after the user explicitly confirms that this window has reloaded. Treat any message that clearly confirms reload as sufficient; otherwise keep waiting or ask one focused confirmation question.

Installation command

npm run release -- --install

Do not manually bump the version first. The release workflow owns the version bump, build, VSIX packaging, verification, and installation. If an earlier failed release already bumped the version, rerunning the release workflow may bump it again; report the final installed version and keep the resulting package.json and package-lock.json changes.

Reload handoff

Use concise wording such as:

Installed AgentLink <version>. Please reload this VS Code window, then tell me when it is back. I will not continue the smoke test until you confirm the reload.

Do not call additional tools after issuing this handoff until the user confirms reload.

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.