Sync Claude/agent metadata with actual .claude tooling - #74
Draft
chbaker0 wants to merge 1 commit into
Draft
Conversation
Document the tracked .claude/ tooling in CLAUDE.md, cross-reference the qemu-boot skill from AGENTS.md's boot section, and refresh the stale status date. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01F4K2FSZaAEDJBCw5bUyvJY
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Addresses #73.
Corrects metadata drift between the human-readable agent docs and the tooling actually tracked under
.claude/. Metadata-only — no code changes.What changed and why
CLAUDE.mdsaid "This file is for Claude-specific notes only; there are none yet." — flatly false now. Replaced it with a short inventory of the tracked.claude/tooling: the project-wideTerseoutput style (.claude/settings.json), theqemu-bootskill, and thesource-grounded-explorersubagent.AGENTS.md— "Booting headlessly and bounding the run" documented the manual QEMU boot dance but never mentioned theqemu-bootskill that encapsulates it; added a cross-reference so the skill is discoverable from the doc it mirrors.AGENTS.md— bumped the staleLast updated 2026-07-21status date (content was materially edited later, in CI: gate clippy over every workspace package #46, without a bump).Out of scope (flagged in #73, not implemented)
External Anthropic-official tooling that could close adjacent gaps — the Claude Code GitHub Action / auto-fix-PR / Routines for the CI-centric verify loop, and the
rust-analyzer-lspmarketplace plugin — is listed as breadcrumbs in the issue, not adopted here.🤖 Generated with Claude Code
Generated by Claude Code