Docs: surface .claude tooling in CLAUDE.md and AGENTS.md - #69
Draft
chbaker0 wants to merge 1 commit into
Draft
Conversation
Co-Authored-By: Claude Opus 4.8 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 #68.
What changed
Metadata-only corrections (no code changes). Three things live in
.claude/— thesource-grounded-explorersubagent, theqemu-bootskill, and the project-wide "Terse" output style — and neither doc mentioned any of them;CLAUDE.mdstill claimed "there are none yet."CLAUDE.md: replaced the stale "there are none yet" line with a short Claude-specific tooling inventory — the Terse output style (enabled viasettings.json), theqemu-bootskill (with a note to prefer it over hand-running the boot steps), and thesource-grounded-explorersubagent.AGENTS.md: added a one-line breadcrumb at the top of "Booting headlessly and bounding the run" pointing at theqemu-bootskill, so an agent reading AGENTS.md alone learns the manual recipe below is what the skill implements.Why
The
qemu-bootskill's own add-commit (2dbe3de) was titled "Update AGENTS.md project status and add qemu-boot skill" but never actually pointed AGENTS.md at the skill, so a fresh agent re-runs ~40 lines of manual QEMU-boot procedure unaware a skill encapsulates it. The rest of AGENTS.md's body claims (CI jobs, clippy gate, cargo aliases, crate layout) were verified accurate against the tree and left unchanged.Skill/subagent opportunities and external-tooling candidates (rust-analyzer-lsp; GitHub MCP / code-review / claude-code-action) are enumerated in #68 as breadcrumbs — intentionally not implemented here.
🤖 Generated with Claude Code
https://claude.ai/code/session_011tFLmmJCMeJDqbKrJsnQc3
Generated by Claude Code