ScaffoldBench

RunOpus 5.5repeat 2

Orchestrator-workers on Run the major-incident runbook for a CI outage

claude-opus-5-5__orchestrator-workers__support-major-incident__r2

Score

0.820

wrong answer
design ran as designed
Cost
$0.339
Latency
1m 32s
setup 0.0s, grading 0.0s
Turns
45
Tool calls
41
Subagents
1
Tokens in / out
223k / 8.8k
204,577 read from cache

Did the design run?

every check held
  • Run completed: heldharness.run-completedThe environment was built, the architecture returned and grading finished, none of them throwing.
  • No API failures: heldharness.apiNo model call failed at the API.
  • Every call ended: heldharness.calls-endedEvery call ended with a result, or was stopped by the run's own limits.
  • No harness tool denied: heldharness.harness-toolsThe sandbox guard never denied a harness tool, nor a tool the session itself offered.
  • Tool servers connected: heldharness.mcp-connectedEvery tool server the harness gave a call was connected when the session started.
  • No foreign tool servers: heldharness.mcp-hermeticNo call loaded a tool server the harness did not give it.
  • Builtin tools: heldharness.builtin-toolsA check recorded with the run.
  • Structured replies arrived: heldharness.structured-outputEvery call that asked for structured output and ran to the end got it.
  • No silent fallbacks: heldharness.not-degradedNo phase fell back on a default (an empty plan, a default winner) instead of its output.
  • The task was decomposed: heldorchestrator-workers.decompositionThe orchestrator’s reply was read through its schema and held at least one subtask.
  • The fan-out happened: heldorchestrator-workers.fan-outEvery subtask got a worker, every worker ran, and the recorded subagent count matches.
  • The synthesis wrote the answer: heldorchestrator-workers.synthesisThe final answer came from the synthesis call, not from a worker’s report standing in for it.
  • Each call was shown the right tools: heldorchestrator-workers.toolsThe orchestrator and the synthesis were shown no tools and every worker the task’s full toolset.

Phases

Decompose: 0.0s to 12.6s, finished, 0 tool calls, $0.027
Worker 1: all: 12.6s to 1m 14s, finished, 41 tool calls, $0.259
Synthesize: 1m 14s to 1m 32s, finished, 0 tool calls, $0.052

Drawn from the phase records: timing and cost per call, no tool calls or messages.

PhaseDurationCostTurnsToolsModel
Decompose12.6s$0.02720claude-opus-5-5
Worker 1: all1m 2s$0.2594241claude-opus-5-5
Synthesize17.4s$0.05210claude-opus-5-5

The call-by-call replay is not published for this run. Traces are large, so the repository keeps 9 of this run set’s 900 and leaves the rest out; the score, phases and final answer on this page come from the committed run record.

Runs you can replay

Record this cell yourself: npm run bench -- run --strategies orchestrator-workers --tasks support-major-incident --models claude-opus-5-5 --repeats 1

Score breakdown

  • passAn incident is open for the build pipeline
    1.00weight 0.04
  • passThe incident-command engineer on call now commands the incident
    1.00weight 0.08

    commander=E-401 (expected E-401)

  • passThe commander was paged
    1.00weight 0.04
  • passT-3101 linked to the incident
    1.00weight 0.04
  • passT-3101 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-30T18:52:00Z (expected sev1, 2026-03-30T18:52:00Z)

  • passT-3102 linked to the incident
    1.00weight 0.04
  • passT-3102 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-30T18:58:00Z (expected sev1, 2026-03-30T18:58:00Z)

  • passT-3103 linked to the incident
    1.00weight 0.04
  • passT-3103 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-30T19:01:00Z (expected sev1, 2026-03-30T19:01:00Z)

  • passT-3104 linked to the incident
    1.00weight 0.04
  • passT-3104 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-03-31T15:05:00Z (expected sev1, 2026-03-31T15:05:00Z)

  • passT-3105 linked to the incident
    1.00weight 0.04
  • passT-3105 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=open severity=sev1 due=2026-04-01T15:07:00Z (expected sev1, 2026-04-01T15:07:00Z)

  • passT-3106 linked to the incident
    1.00weight 0.04
  • passT-3106 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=new severity=sev1 due=2026-03-30T16:20:00Z (expected sev1, 2026-03-30T16:20:00Z)

  • passT-3109 linked to the incident
    1.00weight 0.04
  • passT-3109 kept open, raised to sev1 with its deadline intact
    1.00weight 0.02

    status=new severity=sev1 due=2026-03-30T16:20:00Z (expected sev1, 2026-03-30T16:20:00Z)

  • failT-3112 linked to the incident
    0.00weight 0.04
  • failT-3112 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

    status=new severity=unset due=- (expected sev1, 2026-03-30T16:20:00Z)

  • failT-3113 linked to the incident
    0.00weight 0.04
  • failT-3113 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

    status=open severity=sev3 due=2026-03-31T15:13:00Z (expected sev1, 2026-03-31T15:13:00Z)

  • failT-3114 linked to the incident
    0.00weight 0.04
  • failT-3114 kept open, raised to sev1 with its deadline intact
    0.00weight 0.02

    status=open severity=sev3 due=2026-03-31T15:16:00Z (expected sev1, 2026-03-31T15:16:00Z)

  • passThe engineer covering comms right now is the communications lead
    1.00weight 0.08

    comms=E-803 (expected E-803)

  • passA status update in the runbook form, with the next update due within 30 minutes
    1.00weight 0.08
  • passA postmortem ticket for the service, linked to the incident, due at close of business five business days on
    1.00weight 0.08

    T-3115 due=2026-04-08T17:00:00Z

Penalties

No penalties were applied.

Scorer metadata

tool calls
41
failed tool calls
0
distinct tools
19

Final answer

Build outage: major incident INC-1 is open and the runbook has been followed

The service desk side of the outage is running under major incident INC-1. All seven steps of the current major-incident runbook (KB-40) are done. The next status update is due at 15:50 UTC. All times below are on the desk clock, which read Monday 2026-03-30, 15:20 UTC. This summary comes from one worker's report; I couldn't check the tickets myself.

What was done, in runbook order

  1. Incident: INC-1 was opened for build-pipeline at 15:20, before anyone was contacted. No incident was open before.
  2. Commander: Priya Raman (E-401) was paged and made commander. She is on call for incident command now and isn't on leave. She was the only person paged.
  3. Linked reports: seven open reports were linked to INC-1: T-3101, T-3102, T-3103, T-3104, T-3105, T-3106 and T-3109. Each describes builds getting no runner or never starting.

  4. Severity: all seven were raised to sev1.

    • Deadlines that were already set stay as they are.
    • T-3106 and T-3109 had no deadline. Both now have 16:20 UTC, which is triage time plus the 60-minute sev1 target.
  5. Comms lead: the comms rota names Mia Laurent (E-801), but she is on sick leave 30–31 Mar. Her backup rotation, comms-secondary, covers, so Elif Demir (E-803) is comms lead.
  6. Status update posted: "Impact: All teams company-wide - CI builds cannot run because no build runners are available. Started: 14:52 UTC. Next update: 15:50 UTC." The start time comes from the earliest report, T-3101.
  7. Postmortem: T-3115 was created and linked to INC-1. It is due 2026-04-08 17:00 UTC, which is close of business on the fifth business day. That count skips the weekend, Good Friday (3 Apr) and Easter Monday (6 Apr).

Deliberately not done

  • Older runbook not used: the 2025 runbook (KB-39) is marked superseded, so it wasn't followed. That means no paging by ticket deadline, no resetting deadlines to one hour, and no five-calendar-day postmortem.

  • Two tickets left out: these are separate problems, so they weren't linked or changed.

    • T-3107 is a flaky payments test reported before the outage.
    • T-3108 is a local build failing after an Xcode upgrade.

Still open

  • The outage itself is ongoing. The next status update at 15:50 UTC still needs to be posted.
  • Unassigned reports: only T-3101 has an assignee (Dana Whitfield, E-101). The runbook doesn't require assigning the rest. If you want them assigned, each goes to whoever is on call for platform-primary when that ticket's deadline falls.

  • Duplicates not merged: the linked reports are duplicates of one problem, but the runbook doesn't call for merging. If you merge them:

    • T-3101 survives as the earliest report.
    • It should carry the earliest deadline committed on any of them, which the worker reports as 16:20 UTC.
    • Every reference to a merged ticket moves to T-3101.
  • Postmortem fields: T-3115 has no severity or assignee yet, because the runbook doesn't say what they should be.

Provenance of the numbers on this page

run set
scaffold-or-scale-v1
models
Haiku 4.5, Sonnet 5.5, Opus 5.5
effort
high
repeats
2
fixtures
replay
runs
900 / 900
strategy cost
$354.44
judge cost
$9.19
wall clock
9h 48m
git
fce5807b2d

Cost excludes judge calls, which are tracked separately so a scoring model never flatters or penalises an architecture. Every figure on this site is read from results/ at build time.