check-agent-compatibility

# Check agent compatibility ## Contract | Field | Bound contract | |---|---| | Trigger | Full repository agent-compatibility pass, invoked explicitly by a human | | Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. | | Side effect | Chat output only; target is read-only CLI and review passes. No repository, configuration, or remote state is changed | | Done | A scored compatibility report with prioritized fixes and broken-down dimension results is returned | ## Inputs - Repository path to audit (must be supplied). - Optional scope limit (subdirectory or file glob) narrowing the pass; when omitted the whole repository is audited. ## Procedure 1. Parse scope and bind to the repository. Resolve the repository path to an absolute directory and apply the optional scope limit. Do not widen scope mid-pass. Done when: scope is bound to the repository path and optional limit. 2. Discover agent configuration and instruction surfaces. Scan for: `.claude/` directories (`settings.json`, `commands/`, `hooks/`), `CLAUDE.md` and `AGENTS.md` files, `.cursor/` directories, `plugin.json` or `.claude-plugin/` manifests, `agents/openai.yaml` skill manifests, MCP configuration files (`.mcp.json`, `mcp.json`), and any `skills/*/SKILL.md` trees. Done when: all agent configuration and instruction surfaces within scope are discovered. 3. Validate syntax, schema, and dependency resolution for discovered surfaces. For each surface: parse JSON/YAML synt...