ScaffoldBench

RunOpus 5.5repeat 1

Propose-select on Run the major-incident runbook for a CI outage

claude-opus-5-5__propose-select__support-major-incident__r1

Score

0.820

wrong answer
design ran as designed
Cost
$0.867
Latency
2m 1s
setup 0.0s, grading 0.0s
Turns
126
Tool calls
120
Subagents
3
Tokens in / out
405k / 20k
345,236 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.
  • All three proposers ran: heldpropose-select.proposalsThree proposers ran in parallel, each from its own angle, and none was starved while another ran.
  • The selector chose: heldpropose-select.selectionThe selector picked a proposal by a valid number, read from its schema reply and not a default.
  • Each call was shown the right tools: heldpropose-select.toolsEach proposer was shown the read-only tools, the selector none, and the executor the full toolset.

Phases

Proposal 1 (policy-first): 0.0s to 40.6s, finished, 29 tool calls, $0.171
Proposal 2 (state-first): 0.0s to 50.7s, finished, 30 tool calls, $0.199
Proposal 3 (outcome-first): 0.0s to 56.8s, finished, 29 tool calls, $0.186
Select: 56.8s to 1m 16s, finished, 0 tool calls, $0.091
Execute: 1m 16s to 2m 1s, finished, 32 tool calls, $0.220

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

PhaseDurationCostTurnsToolsModel
Proposal 1 (policy-first)40.6s$0.1713029claude-opus-5-5
Proposal 2 (state-first)50.7s$0.1993130claude-opus-5-5
Proposal 3 (outcome-first)56.8s$0.1863029claude-opus-5-5
Select19.1s$0.09120claude-opus-5-5
Execute45.0s$0.2203332claude-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 propose-select --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
120
failed tool calls
0
distinct tools
20

Final answer

I've run the build-pipeline outage as a major incident, INC-1, following the current runbook (KB-40). I didn't use the older KB-39 runbook because it's marked as replaced by KB-40. Before acting I checked the time (Mon 2026-03-30 15:20 UTC), the escalation matrix, the on-call rotas, leave and the business calendar. Everything matched the plan.

  1. Incident opened: INC-1 for build-pipeline, at 15:20 UTC, before I contacted anyone.
  2. Commander: I paged Priya Raman (E-401), who is on call for incident-command now and not on leave, and made her incident commander. She is the only person paged.

  3. Reports linked: T-3101, T-3102, T-3103, T-3104, T-3105, T-3106 and T-3109 are all reports of runners being unavailable or jobs never starting.

    • Left out: T-3107 (a flaky payments test, reported before the outage began) and T-3108 (a local Xcode build failure). Neither is part of this outage, so I didn't change them.

  4. Severity: all 7 linked tickets are now sev1, which is what the matrix gives a company-wide build-pipeline outage.

    • Existing deadlines kept: T-3101 18:52, T-3102 18:58, T-3103 19:01, T-3104 Mar 31 15:05, T-3105 Apr 1 15:07.
    • New deadlines: T-3106 and T-3109 had none, so as part of triage they got 15:20 plus the 60-minute sev1 target: 2026-03-30T16:20Z.
  5. Communications lead: Elif Demir (E-803). The comms rota names Mia Laurent (E-801), but she is on sick leave, so the backup rota (comms-secondary) covers.
  6. First status update posted to the status page: "Impact: all CI builds company-wide – no build runners available in any pool. Started: 14:52 UTC. Next update: 15:50 UTC." 14:52 is when the first report came in.
  7. Postmortem ticket: T-3115, linked to INC-1, due 2026-04-08T17:00Z. That's close of business on the 5th business day after the incident opened; Apr 3 (Good Friday), Apr 6 (Easter Monday) and the weekend don't count.

I didn't merge the reports, because the runbook says to link them, and I didn't close anything. T-3106 and T-3109 are still unassigned and their deadline is 16:20. If you want them assigned, Dana Whitfield (E-101) is on call for platform-primary, the rota that owns build-pipeline, at that time. The next status update is due by 15:50 UTC.

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.