subagentrubrics

.com durable rubric primitive

← all rubrics

rbc_cowork_feature_adoption — Cowork Feature Adoption Rubric

text · 9 criteria · created 2026-07-01 23:43:40 · source subagentrubrics.com

Scores the second improvement batch this session: an explicit audit of which Claude Cowork features (scheduled tasks, persisted artifacts, model routing, memory/dreams) were and were not adopted while building the subagentjobs workers, with concrete deterministic follow-through rather than a vague "consider using X" note.

Criteria (raw markdown)

# Cowork Feature Adoption Rubric

## Feature Gap Analysis
- The set of unused Cowork features relevant to this repo (scheduled tasks, persisted artifacts, memory stores/dreams, model routing) is enumerated explicitly, not gestured at vaguely
- Each feature is evaluated for actual applicability to this repo's architecture (Cloudflare Workers + D1, not MCP connectors) rather than assumed to fit
- A feature found NOT to fit (e.g. artifacts' sandboxed network blocking non-CDN fetches, which blocks live-refreshing our own HTTPS APIs) is documented as evaluated-and-rejected with the specific technical reason, not silently dropped

## Deterministic Follow-Through
- At least one concrete, checked-in artifact results from the analysis (script, migration, code change) rather than the analysis being purely descriptive
- The artifact is actually run and its output captured as evidence, not assumed to work
- If an interactive Cowork tool call is rejected by the user/approval flow mid-task, the response pivots to a working alternative rather than stalling or silently dropping the goal

## No Regression
- The batch-1 fixes (Display-P3 + reduced-motion on all ~35 sites) are re-verified as still live before claiming batch 2 complete
- The verification method is deterministic and repeatable (a committed script), not a one-off manual check that can't be reproduced next session

## Honest Model-Routing Check
- Confirms whether Fable 5 / Sonnet 5 routing decisions made earlier this session (engineering-coworker -> Fable5, Sonnet-main/Fable-advisor pairing) are still the correct assignment given no new model information, rather than re-litigating them without cause

Raw fields

idrbc_cowork_feature_adoption
titleCowork Feature Adoption Rubric
rubric_typetext
criteria_count9
source_docplatform.claude.com/docs/en/managed-agents/define-outcomes.md
source_sitesubagentrubrics.com
created_at2026-07-01 23:43:40

view as JSON →