brain-audit

# /brain-audit - post-synthesis audit primitive A small composable skill. Takes a list of source file paths and an optional entity name. Runs three checks against the sources. Returns a stable markdown footer that the composing skill pastes beneath its synthesis. The skill does not synthesize, does not query a workspace-wide index, does not write state. It reads the files passed in and scans canonical workspace locations for the named entity. It then runs one LLM call to detect source disagreements, and emits a three-section footer. CEO may also invoke directly for ad-hoc audits. ## Phase 1: Argument parsing and sanity checks ### 1.1 Parse arguments Read `$ARGUMENTS`: - `--sources <paths>` (required): comma-separated. Each path is workspace-relative (paths starting with `/`, `c:\`, or containing `..` traversal are rejected as invalid sources in Phase 1.2). Workspace paths in this repo do not contain commas; if a future path does, the composer must quote it. If `--sources` is absent or empty, return the no-sources footer (Phase 3.5) and exit. - `--entity <name>` (optional): scopes the modality scan. If absent, modality check is skipped and the footer notes "no entity specified." - `--modalities <list>` (optional): comma-separated subset of the canonical list. Default is "all from `references/modalities.md`." ### 1.2 Validate source paths For each path: - File exists -> keep in source set. - File missing -> drop from source set, list under "sources not found" in the f...