agentleFS
Sign inStart free
Google CloudKnown publisherGoogleCloudPlatform/devrel-demos/ai-ml/dev-signal/.agent/skills/gcp-agent-shadow-deployer/SKILL.md

gcp-agent-shadow-deployer

Skill397 starsChanged 12 days agoApache-2.0View on GitHub

Implements the "Dark Canary" pattern for Cloud Run, allowing agents to be evaluated in production without serving user traffic.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Tag with Commit Hash: Every deployment is tagged with the current Git commit hash (e.g., c-a1b2c3d).

    line 19
  2. Distinctive:

    Promotion: If evaluation metrics (Final Response Match, Tool Use Quality) pass, promote the revision to 100% traffic.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

gcp-agent-shadow-deployer

This skill helps you implement safe, automated rollouts for your AI agents. Based on the "Evaluating Agent Performance" codelab, it uses Cloud Run revision tagging to deploy a Shadow Revision for evaluation before promoting it to live traffic. This enables System-Level Evaluation (latency, network, auth) rather than just unit testing.

Usage

Ask Antigravity to:

  • "Deploy a shadow revision of my agent for evaluation"
  • "Tag my new Cloud Run revision with the Git SHA"
  • "Promote my shadow revision to 100% traffic"

Shadow Pattern ("Dark Canary")

  1. Tag with Commit Hash: Every deployment is tagged with the current Git commit hash (e.g., c-a1b2c3d).
  2. --no-traffic: The revision is deployed with 0% traffic.
  3. Shadow URL: Access the revision via a dedicated tag URL: https://[TAG]---[SERVICE]-[HASH]-[REGION].a.run.app.
  4. Promotion: If evaluation metrics (Final Response Match, Tool Use Quality) pass, promote the revision to 100% traffic.

Shell Template

Refer to scripts/deploy_shadow.sh for the standard implementation.

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.

Check your setup, free