backlog(B-0791 P2): Microsoft VSCode-native (NOT Anthropic) is standardizing multi-harness ontology across .claude/.kiro/.cursor/.gemini/.codex — IDE-platform-level external pull (Aaron 2026-05-26 surface intel + correction)#5101
Merged
AceHack merged 3 commits intoMay 26, 2026
Conversation
…ntology — Agents/Skills/Hooks/MCP/Instructions as uniform vocabulary across .claude/.kiro/.cursor/.gemini/.codex Aaron 2026-05-26 surfaced screenshot intel from Anthropic VSCode Claude Code extension's "new Agents window" session-launch surface: > "the new Agents window seems to be standardized ontology across > multiple harnesses in one vscode window they are definting what > are agents and skills and hooks and plugins and instruction > etc... they are trying to standardize it seems." The screenshot showed: - Customizations panel: Agents (19), Skills (263), Instructions (1), Hooks (25), MCP Servers (11) — counts likely aggregate across all five .claude/.kiro/.cursor/.gemini/.codex dirs - File-tree: all five harness dirs visible as peer surfaces - Session list: 8+ background-worker sessions with adjective-gerund- noun auto-naming (ABSTRACT-HATCHING-YAO, etc.) — opaque - "What are you building?" prompt — assumes greenfield rather than autonomous-loop continuation Two load-bearing implications for Zeta substrate strategy: 1. Anthropic's standardization is convergence ON what Zeta already does (5 personas × 5 harnesses; per-harness rule loading per .claude/rules/claude-code-loading-taxonomy.md). Validates the architecture; removes work. 2. Zeta-specific extensions (personas, sub-personas, maintainers, bus envelopes, cluster software factory) need to compose WITH the ontology, not replace it. Vocabulary-mapping document needed. Sub-targets: - Surface intel captured (this row) - Vocabulary-mapping doc (sub-target 2; small follow-on) - VSCode-extension-UX observations (sub-target 3; separate row) - Quarterly re-check of standardization direction (sub-target 4) Composes with B-0759/B-0776/B-0780/B-0782/B-0790 + .claude/rules/agent-roster-reference-card.md + .claude/rules/claude-code-loading-taxonomy.md + .claude/rules/peer-call-infrastructure.md + .claude/rules/otto-channels-reference-card.md. Out-of-scope: specific VSCode UX issues (separate small row); upstream contribution to VSCode extension (separate row at upstream-contribution scope); agent-worktree-hygiene observations from same screenshot tracked under B-0750. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…nthropic-specific (Aaron 2026-05-26 critical correction) Aaron 2026-05-26 follow-up correction during mid-iter-4.4 verification + B-0791 PR-opening: > "The Agents window is not anthropic is Microsoft i think > vscode native cross harness not Anthropic" Substantial implication shift: this is PLATFORM-level standardization (Microsoft / VSCode upstream), NOT VENDOR-level standardization (Anthropic pulling their own primitives). The platform-vs-vendor distinction is load-bearing: - Vendor standardization can be ignored by other vendors - IDE-platform standardization is what the developer's daily tool enforces — every harness either fits the ontology or gets second-class IDE integration Stronger selection pressure toward convergence. Changes: - Filename: vscode-extension-...-anthropic-pulling-... → vscode-native-...-microsoft-not-anthropic-... - Title: "Anthropic VSCode extension's" → "Microsoft VSCode-native"; added explicit "NOT an Anthropic- specific surface" disclaimer - Body: all attribution refs swapped Anthropic → Microsoft / VSCode-native (preserving only the disclaimer + Aaron's verbatim quote) - Added platform-vs-vendor distinction subsection explaining the stronger selection pressure - "Microsoft / VSCode-native ontology primitive" used as table header - Quarterly re-check now scoped to "Microsoft / VSCode's standardization direction" not Anthropic's Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Adds a new P2 backlog row (B-0791) capturing surfaced intel that Anthropic’s VSCode extension UI is converging on a standardized multi-harness ontology (Agents / Skills / Hooks / MCP Servers / Instructions / Plugins), and records implications for Zeta’s multi-harness substrate strategy.
Changes:
- Adds backlog row B-0791 documenting the VSCode “Agents window” ontology convergence signal and its implications for Zeta.
- Introduces an initial Anthropic→Zeta vocabulary mapping table and identifies follow-on work items (mapping doc + separate UX row).
Per non-required `check docs/BACKLOG.md generated-index drift` CI warning surfaced after PR #5101 opened — `BACKLOG_WRITE_FORCE=1 bun tools/backlog/generate-index.ts` regen. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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
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.
Summary
Aaron 2026-05-26 surfaced screenshot intel from VSCode-native "Agents window" surface, then critically corrected the attribution mid-PR:
Critical correction: this is Microsoft VSCode-native cross-harness substrate, NOT an Anthropic-specific extension surface. Platform-level standardization, not vendor-level.
What the screenshot shows
Why platform-vs-vendor matters
Much stronger selection pressure toward convergence.
Implications for Zeta
Composes with
Out of scope
Test plan
🤖 Generated with Claude Code