ai-ide-audit

# IDE Support Audit ## Quick start ``` /ai-ide-audit all # audit all platforms /ai-ide-audit github-copilot # Copilot only /ai-ide-audit claude-code # Claude Code only /ai-ide-audit antigravity # Antigravity app + agy CLI /ai-ide-audit all --fix # audit + auto-fix P0 issues ``` ## Workflow Strict evidence-based audit of IDE support in ai-engineering. No assumptions — every claim cites a file path. Output is always the structured audit document, no matter how many IDEs are requested. 1. **Write the report skeleton first** from `references/report-template.md` BEFORE collecting evidence. 2. **Dispatch a single `Explore` subagent** to read instruction surfaces, hook configs, mirror dirs, and `manifest.yml` counts. 3. **Classify each capability per platform** (SUPPORTED / PARTIAL / UNSUPPORTED) using the capability matrix. 4. **Run spec-107 advisory checks** (advisory-only per NG-11): - **Check 6** — agent naming consistency cross-IDE: every agent file's frontmatter `name:` must equal its slug. - **Check 8** — generic instruction-file count scan: walk every CLAUDE.md / AGENTS.md / copilot-instructions.md and validate `## Skills (N)` + `## Agents (N)` headers vs canonical counts. 5. **With `--fix`**, auto-remediate P0 issues only; re-run mirror sync; verify tests still pass. > Detail: see [evidence collection (instruction surfaces, hooks, mirrors, sync script)](references/evidence-collection.md), [capability matrix + advisory checks + aut...