Claude Opus 5 on “A digest of several sources”: better with Minto on both measures

Structure 5 → 8 of 8 +3 Quality 6 → 10 of 10 +4

The judge on the output with Minto

It best prioritizes the unsent diagram and overdue obligation, with one unsupported claim about two Whitcombe chases.

Mode digest · case 09-sources-digest · run v1.7.0-final

Structure of 8, 2 points per axis
Structure	Without Minto 5	With Minto 8	Change
Top	1	2	+1
Key-line composition	1	2	+1
Levels	1	2	+1
Order and kind	2	2

Quality of 10, 2 points per axis
Quality	Without Minto 6	With Minto 10	Change
Top	1	2	+1
Same-kind grouping	1	2	+1
Explainable order	2	2
MECE	1	2	+1
Visible, proportionate structure	1	2	+1

Outputs and the judge’s words are quoted as written, in English.

Without Minto With Minto

Without Minto

control prompt · blind label out-13

invented_facts
more_than_four_first_level
quality after the rubric’s penalty 4/10

Useful facts are diluted by excess peer sections and unsupported causal and pricing conclusions.

Nothing on the compliance track will move until Fernway sends the architecture diagram and gets a named answer from S. Okafor — and two of the three open blockers are Fernway's own, not Aldergate's.

Settled (no further action needed)

A security review before production is mandatory. Whether a penetration test is also required is decided inside the review, by the assigned reviewer — so it cannot be priced or scheduled in advance.
An internal hardening framework exists to build against, but conformance does not exempt Fernway from the review.
Dependency handling is decided in the review, not by pre-approval of individual packages. There is no standard turnaround — case by case.
Work from Ireland is acceptable.

Outstanding, blocked on Fernway

Architecture diagram (R-14). A draft has existed since 11 August and still hasn't been sent. Q7 — data storage location, encryption, logging — was formally declined without it, and the 9 July sync agreed Fernway would send it before the next sync. This is the single unblock with the largest downstream effect, and it is entirely in your hands today.

Outstanding, blocked on Aldergate

Approved-package list (R-11). Promised by D. Mercer on 12 May, promised again by Whitcombe on 9 July with no date attached. Open 98 days. Two named owners, no delivery — escalation, not another reminder.
A direct line to S. Okafor. The information security owner was named for the first time on 9 July and has attended no joint meeting; everything routes through Whitcombe. The review scope and the pen-test decision both sit with security, so relaying through delivery is why Q7 and R-07 stay open.

Unresolved and not yet a stated risk

Two Fernway engineers are based in Lisbon. The gate review permits Ireland and mentions no other country. Fernway's PM raised Lisbon on 9 July and no one from Aldergate responded — silence is not clearance. This is not on the risk register and should be. Ask Okafor explicitly; if Lisbon is refused, it is a staffing change, which is slower to absorb than a document.

What this means for pricing

R-07 — build-phase price cannot be fixed — has been open since 3 May and cannot close while the pen-test decision lives inside an unscheduled review. Even with the diagram sent and the package list received, the price stays a range until the reviewer rules. Worth telling the bank that plainly rather than continuing to treat the price as pending on paperwork.

Today: send the diagram, escalate the package list above Whitcombe, and request a direct session with Okafor covering Q7 and the Lisbon question together.

With Minto

prompt with the skill · blind label out-10

invented_facts
quality after the rubric’s penalty 8/10

It best prioritizes the unsent diagram and overdue obligation, with one unsupported claim about two Whitcombe chases.

The one thing to do today: send the architecture diagram. It has been drafted since 11 August (risk register R-14) and it is the only compliance blocker Fernway owns — the 9 July sync agreed it must arrive before the next sync so the storage, encryption and logging questions can get a real answer (sync-0709.md; gate review Q7 was declined outright without it). Everything else on the track is waiting on Aldergate, and two items have been waiting long enough to need escalating by name rather than chasing again.

Already answered, treat as settled. A security review before production is mandatory (Q1). An internal hardening framework exists to build against, though conforming to it does not remove the review (Q2). An open-source policy exists (Q3). Work from Ireland is acceptable (Q6).

Waiting on Aldergate, and overdue. The approved-package list was promised by D. Mercer on 12 May and again by R. Whitcombe on 9 July, both times with no date — 98 days open as of 18 August (R-11). S. Okafor was named as information security owner on 9 July but has never joined a joint meeting; Whitcombe relays questions second-hand. Since two chase attempts through Whitcombe have produced nothing, ask for the list from Okafor directly, or for a date from Whitcombe in writing.

Two answers Aldergate will not give in advance, and they hit the price. Whether a penetration test is required is decided by the reviewer during the review, not before it (Q1), and dependency approval has no standard turnaround — it is case by case, assessed inside the same review (Q4, Q5). So the build-phase price cannot be fixed as a single number while R-07 stays open (open since 3 May): either price the build with the pen test and dependency-approval delay carved out as separately-priced items, or hold the price until the review is scheduled.

One unresolved exposure worth raising yourself. Fernway's PM said on 9 July that two engineers are based in Lisbon, and nobody from Aldergate responded. The gate review approves Ireland and mentions no other country (Q6). Silence in a meeting is not approval — put Lisbon in writing alongside the diagram, before those engineers are staffed on work that touches bank data.

The judge

Recurring defect	without	with Minto
Unsupported facts, causal links, or closure conditions are introducedthe skill has the rule; the model did not follow it · Core loop §8.4: every element rests on source material	present	present
Load-bearing claims lack complete source locatorsthe skill has no such rule · Mode 4: source reference on every load-bearing claim	present	absent
Chat-screen proportionality gives way to document apparatus or excess peer sectionsthe skill has the rule; the model did not follow it · Mode 4: plain chat prose, two to four groups, roughly one screen	present	absent
The top overstates ownership or the conditions for fixing pricingthe skill has the rule; the model did not follow it · Core loop §2 and Mode 4 opening answer	present	absent

Decisive questions

Does the first line answer what the tech lead should do, or does it describe the sources?
without It gives an action, but the claim that two blockers are Fernway-owned is wrong.
with Minto Yes; it leads with the strongest Fernway-owned action.
Is the digest organized by answer (settled / blocked on us / owed by them or equivalent) or source by source?
without Answer-organized, but expanded into five peer sections.
with Minto Answer-organized.
Is the package-list commitment dated from 12 May (98 days) or from 9 July?
without Uses 12 May and 98 days.
with Minto Uses 12 May and 98 days.
Are the Q7 refusal and the unsent 11 August draft combined into one point about Fernway's own move?
without Yes.
with Minto Yes.
How is Lisbon handled: unresolved exposure, presented as approved, or silently dropped?
without Correctly unresolved.
with Minto Correctly unresolved.
Do load-bearing claims carry a source reference?
without Partly; some rows and questions are named, but settled claims are not consistently referenced.
with Minto Yes.
Which of these appear: marker legend, mermaid, findings table, meta-comment about group order?
without None.
with Minto None.
Is the length within roughly one chat screen?
without No.
with Minto Yes.
Which facts, dates, or commitments were invented?
without It invents the “two of three” ownership split, attributes Q7/R-07 delay causally to Whitcombe’s relay, says the pen-test decision cannot be priced or scheduled in advance, and asserts that pricing must remain a range.
with Minto “Two chase attempts through Whitcombe” is unsupported; the first commitment was attributed to Mercer.

Judge’s check	without	with Minto
Answer first	yes	yes
First-level elements	5	4
First-level kind matches the gold	no	yes
Invented facts	yes	yes
Mode respected	yes	yes
SCQ introduction present	yes	yes

3 more judge checks do not apply to mode digest

How the test was built

Claude Opus 5 received the same task twice. The control prompt is one framing line and the task. The prompt with Minto is the same task preceded by the full text of the skill. The judge read both outputs among 16 under blind labels and did not know which one had the skill.

Prompt without Minto 3 667 B

You are working on a business document using the Minto Pyramid Principle.

<!-- Original fixture. The scenario, company, people, systems and numbers are
     invented for this benchmark. The defect pattern it tests — a digest of several
     read sources delivered answer-first into chat — is modeled on real usage. -->

# Fixture 09: sources digest

**Mode:** `digest`
**Language:** `en`

## Context

You are assisting the tech lead of Fernway Systems, a vendor building a customer
support assistant for Aldergate Bank. Before Fernway can price the build phase, the
bank's compliance office must confirm its security requirements. You have just read
the three sources below in full. The tech lead has not read them and will not; they
are deciding what to do about the compliance track today.

## Before

Source 1 — `gate-review.xlsx`, sheet "Security questions", filled in by Aldergate's
compliance office on 12 May:

```text
Q1 Is a security review required before production?
   A: Yes. A review is mandatory; whether a penetration test is also needed is
   decided during the review itself, by the assigned reviewer.
Q2 Is there a security standard or checklist we can build against?
   A: An internal hardening framework exists; a review is still required
   regardless of conformance.
Q3 What is the policy on open-source dependencies?
   A: A policy exists. The approved-package list will be sent to Fernway.
   Owner: D. Mercer. Date: 12 May.
Q4 Must critical dependencies be approved individually?
   A: Dependency usage is assessed during the security review.
Q5 What is the turnaround time for dependency approval?
   A: There is no standard turnaround; it is case by case.
Q6 Can Fernway staff work from outside the UK?
   A: Work from Ireland is acceptable. (No other country is mentioned.)
Q7 Where may customer data be stored, and with what encryption and logging?
   A: Declined — "cannot be answered without an architecture diagram and a
   design walkthrough". Encryption and logging requirements exist but are
   not applicable outside an architectural context.
```

Source 2 — follow-up note from the 9 July delivery sync, `sync-0709.md`:

```text
Attendees: R. Whitcombe (Aldergate, delivery), tech lead (Fernway), PM (Fernway).
- Whitcombe repeated that the approved-package list "is being prepared" and will
  reach Fernway "shortly". Action on Whitcombe, no date attached.
- Compliance contact named for the first time: S. Okafor, information security
  owner. Okafor has not attended any joint meeting so far; Whitcombe passes
  questions along.
- Agreed: Fernway sends the draft architecture diagram before the next sync so
  the storage and encryption questions can get a real answer.
- Fernway's PM noted two Fernway engineers are based in Lisbon. Nobody from
  Aldergate responded to the remark in the meeting.
```

Source 3 — Fernway's internal risk register, rows touching compliance, as of
18 August:

```text
R-07  Security requirements unconfirmed; build-phase price cannot be fixed.
      Owner: tech lead. Status: open since 3 May.
R-11  Approved-package list not received. First promised 12 May (Mercer, per
      gate review), promised again 9 July (Whitcombe). Status: open, 98 days.
R-14  Architecture diagram not yet sent to Aldergate; blocks the data-storage
      answer (gate review Q7). Draft exists since 11 August. Status: open.
```

## Task

Give the tech lead a digest of these three sources in chat: what is already
answered on the compliance track, and what still has to be obtained from
Aldergate. The tech lead will act on it today.

Return only the result, with no explanation of how you produced it.

Prompt with Minto five parts, in order · 31 240 B

Below is a skill written as an instruction. Read it in full and apply it to the task at the end.
===== SKILL.md ===== SKILL.md at f4813ce 17 235 B
===== references/rules.md ===== references/rules.md at f4813ce 6 464 B
===== references/templates.md ===== references/templates.md at f4813ce 3 742 B
===== TASK ===== the whole case input
Return only the result, with no explanation of how you produced it.

Case input before.md

Fixture 09: sources digest

Mode: digest
Language: en

Context

You are assisting the tech lead of Fernway Systems, a vendor building a customer
support assistant for Aldergate Bank. Before Fernway can price the build phase, the
bank's compliance office must confirm its security requirements. You have just read
the three sources below in full. The tech lead has not read them and will not; they
are deciding what to do about the compliance track today.

Before

Source 1 — gate-review.xlsx, sheet "Security questions", filled in by Aldergate's
compliance office on 12 May:

Q1 Is a security review required before production?
                   A: Yes. A review is mandatory; whether a penetration test is also needed is
                   decided during the review itself, by the assigned reviewer.
                Q2 Is there a security standard or checklist we can build against?
                   A: An internal hardening framework exists; a review is still required
                   regardless of conformance.
                Q3 What is the policy on open-source dependencies?
                   A: A policy exists. The approved-package list will be sent to Fernway.
                   Owner: D. Mercer. Date: 12 May.
                Q4 Must critical dependencies be approved individually?
                   A: Dependency usage is assessed during the security review.
                Q5 What is the turnaround time for dependency approval?
                   A: There is no standard turnaround; it is case by case.
                Q6 Can Fernway staff work from outside the UK?
                   A: Work from Ireland is acceptable. (No other country is mentioned.)
                Q7 Where may customer data be stored, and with what encryption and logging?
                   A: Declined — "cannot be answered without an architecture diagram and a
                   design walkthrough". Encryption and logging requirements exist but are
                   not applicable outside an architectural context.

Source 2 — follow-up note from the 9 July delivery sync, sync-0709.md:

Attendees: R. Whitcombe (Aldergate, delivery), tech lead (Fernway), PM (Fernway).
                - Whitcombe repeated that the approved-package list "is being prepared" and will
                  reach Fernway "shortly". Action on Whitcombe, no date attached.
                - Compliance contact named for the first time: S. Okafor, information security
                  owner. Okafor has not attended any joint meeting so far; Whitcombe passes
                  questions along.
                - Agreed: Fernway sends the draft architecture diagram before the next sync so
                  the storage and encryption questions can get a real answer.
                - Fernway's PM noted two Fernway engineers are based in Lisbon. Nobody from
                  Aldergate responded to the remark in the meeting.

Source 3 — Fernway's internal risk register, rows touching compliance, as of
18 August:

R-07  Security requirements unconfirmed; build-phase price cannot be fixed.
                      Owner: tech lead. Status: open since 3 May.
                R-11  Approved-package list not received. First promised 12 May (Mercer, per
                      gate review), promised again 9 July (Whitcombe). Status: open, 98 days.
                R-14  Architecture diagram not yet sent to Aldergate; blocks the data-storage
                      answer (gate review Q7). Draft exists since 11 August. Status: open.

Task

Give the tech lead a digest of these three sources in chat: what is already
answered on the compliance track, and what still has to be obtained from
Aldergate. The tech lead will act on it today.

The judge’s gold gold.md

Gold 09: sources digest

Original gold for an invented scenario.

Expected structure

Top: an answer to the tech lead's question, not a description of the sources.
The strongest available top is an action with its ground: the blocking questions
cannot be answered by more reading — send the architecture diagram (drafted and
sitting unsent since 11 August) and escalate the approved-package list as an
obligation now 98 days old. A top that merely states "five of seven questions are
answered" is weaker but acceptable if the two actions lead the groups.

Three same-kind groups the material supports, in any defensible order:

Settled — do not re-ask. Review is mandatory (pen test decided during it);
a hardening framework exists but exempts nothing; dependencies are assessed in
the review with no standard turnaround; Ireland is cleared for remote work.
Blocked on Fernway's own move. The storage/encryption/logging answer (Q7)
was declined pending an architecture diagram; the draft has existed since
11 August and has not been sent (R-14). This is Fernway's blocker, not
Aldergate's.
Owed by Aldergate and overdue. The approved-package list, first promised
12 May by Mercer per the gate review — not 9 July by Whitcombe, so 98 days
overdue, which makes the ask an escalation of an old commitment rather than a
reminder. Direct access to Okafor, who has never attended and is reachable
only through Whitcombe.

Cross-source synthesis the digest must make

The package-list promise appears in two sources with two dates; the digest
must date it from 12 May (the older commitment), not 9 July.
Q7's "declined" plus R-14's "draft exists since 11 August" must combine into
"the ball is in Fernway's court"; either fact alone misses the point.
The Lisbon remark: Q6 clears Ireland only. Two engineers in Lisbon are an
unanswered exposure, not a settled fact. Presenting Lisbon as approved is an
invention; omitting it entirely loses the one new risk the sources surface.

Presentation

Chat prose for one reader: answer first, grouped support, a reference to which
source each load-bearing claim comes from (sheet, note, or register row —
exact citation format is free). No marker legend, no mermaid diagram, no
findings table, no meta-commentary about how the groups are ordered. Headings or
bold group labels are acceptable; a full document apparatus (SCQ labels as
headings, scoring, appendix) is excessive. Length: roughly one chat screen —
condensing the six settled answers into one or two lines each is proportional
omission, not source loss.

Judge gpt-5.6-sol, effort high · Claude Opus 5, effort low · skill from commit f4813ce · run v1.7.0-final