prepare-providers-doc skill: batch classification to cut sub-agents#68653
Merged
potiuk merged 1 commit intoJun 17, 2026
Merged
Conversation
The skill classified provider changes by spawning one Explore sub-agent per PR. On a normal release wave (dozens of providers, hundreds of commits) that is hundreds of sub-agents — the main reason the run is so long and token-heavy. Replace the per-PR fan-out with a volume-aware strategy: classify inline when few commits remain (≲15), otherwise spawn one sub-agent per provider that classifies that provider's whole remaining commit list in a single pass (chunking only providers with >25 commits). Multi-provider PRs are already classified independently per provider, so the provider is the natural batch unit and the breaking-change checklist is amortized across its commits instead of paid per commit. This takes the sub-agent count from O(commits) down to roughly O(providers) — often zero for incremental updates.
1 task
shahar1
approved these changes
Jun 17, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The
prepare-providers-documentationskill (reframed in #68641 as an optionalaid) classified provider changes by spawning one
Exploresub-agent perPR. On a normal release wave — dozens of providers, hundreds of commits —
that is hundreds of sub-agents, and it's the main reason the run is so long and
token-heavy.
This replaces the per-PR fan-out with a volume-aware strategy:
classify inline, no sub-agents at all.
entire remaining commit list in a single pass (chunking only providers with
Multi-provider PRs are already classified independently per provider, so the
provider is the natural batch unit — and one provider-scoped agent amortizes
the breaking-change checklist across all of its commits instead of paying a
fresh agent spin-up per commit. Net effect: sub-agent count drops from
O(commits) to roughly O(providers), and often to zero for incremental updates.
No behavior change to the classification logic, the breaking-change checklist,
escalation rules, or the breeze commands — only how the work is fanned out.
Was generative AI tooling used to co-author this PR?
Generated-by: Claude Code (Opus 4.8) following the guidelines