Edition of Tuesday 17 November 2026

Windows 11 Is Collecting Data on Which Coding Agents and Developer Tools You Use

Comments on “Windows 11 Is Collecting Data on Which Coding Agents and Developer Tools You Use”

Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked

Security researcher Xusheng Li reverse engineered MissionControlAggregator.dll in Windows 11 and found it flags which coding agents (Codex, Claude, Copilot, Cursor) and developer tools (Python, GCC, dotnet) have run, using only executable names. The result is a bitmap sent as a Segments.SubCohorts event, queued for upload when optional diagnostics are on, which was the default in his US setup. The feature was active on his ARM64 VM but disabled in the public ISO baseline. Matching is by file name, and the findings come from one researcher's tests.

Read the original at xusheng.dev. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 8 of 122 with a score of 0.70. The panel rated it highest on new information (0.90) and technical depth (0.89), lowest on significance (0.63). Placed No. 8, No. 12 by score alone: the placement terms moved other stories past it.

AI judgeJudge 2claude-haiku-5-5
Detailed reverse-engineering with reproducible evidence (ETW sessions, process IDs, saved state) on telemetry collecting coding-agent usage; significant privacy angle for builders, though scope is limited to one Windows component on tested builds.
AI judgeJudge 3gpt-5.6-luna
Detailed reverse engineering, controlled tests, ETW tracing, persistence inspection, and upload-queue evidence make this technically strong and actionable. It is highly relevant to AI-tool users, Windows administrators, and privacy-conscious builders, with modest uncertainty around configuration breadth.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.70total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.63
  • Reader interest0.85
  • Audience breadth0.69
  • Practical relevance0.65
  • Substantiated0.85
  • Technical depth0.89
  • New information0.90
  • Counts against: Promotional0.03
  • Counts against: Overclaim0.33

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.650.550.680.630.13+0.24+0.151
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.790.900.860.850.11+0.26+0.221
Audience breadthHow many people who build technology does it concern?0.780.700.580.690.20+0.13+0.089
Practical relevanceHow useful is it to someone who builds software or tech products?0.720.600.640.650.12+0.22+0.144
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.960.720.860.850.24+0.05+0.042
Technical depthHow technically substantive is it?1.000.800.860.890.20+0.05+0.044
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.830.900.960.900.13+0.05+0.045
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.040.030.010.030.03−0.19−0.005
OverclaimDo the headline or conclusions claim more than the body supports?0.440.300.240.330.20−0.11−0.036
Sum of contributions+0.695
Claim-check penalty0.000
Total, as published0.695

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #8 on Rubric, 17 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-17/8/"><img src="https://rubric.hrih.si/badge/2026-11-17/8.svg" alt="Ranked #8 on Rubric, 17 Nov 2026" width="238" height="28"></a>

Claim check

Claim check: 8 no source given. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.

  1. No source givenCausal conclusion

    MissionControlAggregator.dll in Windows 11 records which coding agents and developer tools have been used, saves that locally, and reports it to Windows Diagnostics.

    The article gives no link or citation for it.

    The article says

    “a running Windows component that records which coding agents and developer tools have been used, saves that information locally, and reports it to Windows Diagnostics”

    The source says

    No source to compare with.

  2. No source givenVersion

    The feature guarding the new agent checks is named CLICodingAgentUsage, with feature ID 62580080.

    The article gives no link or citation for it.

    The article says

    “CLICodingAgentUsage, feature ID 62580080”

    The source says

    No source to compare with.

  3. No source givenCausal conclusion

    The aggregator subscribes to existing Windows events (KernelProcess.AppStateChangeSummary, Win32kTraceLogging.AppInteractivitySummary, WSL Exec events) rather than scanning processes itself.

    The article gives no link or citation for it.

    The article says

    “Following Aggregator::OnLoad revealed that it subscribes to existing Windows events instead”

    The source says

    No source to compare with.

  4. No source givenGeneralization

    The component records only a bitmap of which agents were observed, discarding runtime, focus time, interaction counters and resource usage from the source events.

    The article gives no link or citation for it.

    The article says

    “This component appears to discard those details and record only a bitmap of which agents were observed”

    The source says

    No source to compare with.

  5. No source givenVersion

    On the author's Windows 11 ARM64 VM (build 26200.9974), CLICodingAgentUsage was already enabled and DiagTrack was running automatically, with the DLL loaded in AggregatorHost.exe.

    The article gives no link or citation for it.

    The article says

    “CLICodingAgentUsage was already enabled as a service experiment. I had not manually enabled the feature”

    The source says

    No source to compare with.

  6. No source givenNumber

    Copying cmd.exe to codex.exe was enough for the component to recognize it as Codex and emit a Segments.SubCohorts event with CliAgentSubCohorts value 4.

    The article gives no link or citation for it.

    The article says

    “The value 4 is 1 << 2: the Codex CLI bit”

    The source says

    No source to compare with.

  7. No source givenCausal conclusion

    When optional diagnostic data is allowed, Windows queues the coding-agent usage report for upload to Microsoft; the event is marked isRequired false.

    The article gives no link or citation for it.

    The article says

    “When optional diagnostic data is allowed (enabled by default in the US setup I tested), Windows queues the coding-agent usage report for upload to Microsoft”

    The source says

    No source to compare with.

  8. No source givenNumber

    On a clean Windows 11 Home ARM64 install from the latest official ISO with US region, optional diagnostic data was enabled by default (AllowTelemetry was 3).

    The article gives no link or citation for it.

    The article says

    “After completing setup with those defaults, AllowTelemetry was 3, confirming that optional diagnostic data was enabled”

    The source says

    No source to compare with.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 415 pts, front page

Discussion on Hacker News

Recorded for context only, checked 17 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “Windows 11 Is Collecting Data on Which Coding Agents and Developer Tools You Use”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.