agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/chaos-studio/copilot-cli-plugin/skills/run-scenario/SKILL.md

run-scenario

Skill3 starsChanged 5 months agoMITView on GitHub

Execute a ScenarioConfiguration and stream ScenarioRun status with per-action breakdown until terminal state.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    If you are an autonomous agent with no user to prompt, use chaos_execute_scenario + chaos_get_scenario_run (MCP) for a non-interactive …

    line 14
  2. Very specific:

    All execution and status-streaming logic lives in scripts/Invoke-RunScenario.ps1.

    line 20
  3. Very specific:

    Run start via az chaos scenario run start --skip-validation --no-wait (validation already gated upstream)

    line 58

≈ “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

RunScenario — Scenario Execution & Status Streaming

⛔ ABSOLUTE RULE: Do NOT improvise, skip, or substitute any step. On ANY error, STOP and wait for the user.

When to use this skill (vs. the MCP server)

This skill is the human-interactive path: it reads run context from startchaos-state.json, renders status cards, and persists the run result. Use it when there is a user in the loop.

If you are an autonomous agent with no user to prompt, use chaos_execute_scenario + chaos_get_scenario_run (MCP) for a non-interactive run-and-poll flow. Cancellation: chaos_cancel_scenario_run. See mcp/README.md.

Both surfaces target Microsoft.Chaos 2026-05-01-preview and use the local az login session for auth.

How It Works

All execution and status-streaming logic lives in scripts/Invoke-RunScenario.ps1. The script handles confirmation gating, starting the run via az chaos scenario run start --skip-validation --no-wait, ScenarioRun ID resolution (start result + run list fallback), per-poll status rendering via az chaos scenario run show, terminal-state detection, and the final summary.

The AI orchestrator's only job is:

  1. Set $env:STARTCHAOS_STATE_PATH to ${SESSION_DIR}/startchaos-state.json.
  2. Run the script.
  3. Handle exit codes (see below).

The script takes no parameters: configuration name, scenario, and workspace are all read from state.

Prerequisites

  • state.setup.status == "done" (configuration must exist and be validated)
  • state.setup.configuration.id populated

Running the Script

$env:STARTCHAOS_STATE_PATH = "<session-dir>/startchaos-state.json"
& "<skill-dir>/scripts/Invoke-RunScenario.ps1"

For non-interactive sessions, set $env:STARTCHAOS_NONINTERACTIVE=1 to skip the confirmation prompt.

Exit Codes → AI Actions

ExitMeaningAI Action
0Run reached a terminal state (Succeeded / Failed / Canceled)Done — final card already rendered by script. Inspect state.run.status for terminal classification.
1Hard error before/during executionSTOP. Render the error from script output. Wait for user. State has run.lastError.

Cancellation

On Ctrl+C, the script invokes ScenarioRuns_Cancel (POST .../runs/{runId}/cancel) best-effort and persists state.run.lastError = "user-cancelled".

What the Script Handles (no AI logic needed)

  • Confirmation card with scenario, parameters, and scope summary (suppressed when STARTCHAOS_NONINTERACTIVE=1)
  • Run start via az chaos scenario run start --skip-validation --no-wait (validation already gated upstream)
  • ScenarioRun ID resolution from the start result, with az chaos scenario run list fallback
  • Per-poll status via az chaos scenario run show: top status, elapsed time, per-action scenarioRunSummary[] table, resource count, error counts
  • Terminal-state detection (Succeeded, Failed, Canceled) and final summary card
  • Atomic state writes with error envelopes
  • Cancellation handling

Related Skills

  • setup-scenario — must complete before this skill
  • chaos-impact — post-run Azure Monitor impact synthesis
  • start-chaos — orchestrator that invokes this skill

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