Plugin Claude Code
Multi-language systematic codebase X-ray analysis (Python, Java, JavaScript, TypeScript, SQL, PL/SQL, Rust) - analyzes architecture, traces data flows, detects anti-patterns, and generates structured documentation for onboarding, architecture review, or code documentation. Root of the review and documentation…
Agent
Runs Flow Tracing and Semantic Understanding over one partition, reading every partition's structure and interface output so flows and contracts can cite cross-partition boundaries, and writing 03-flows.md and 04-semantics.md into its owned partition directory. TRIGGER WHEN: spawned by /codebase-xray:team-analyze in…
Agent
Runs Pattern and Risk Detection plus Documentation Health over one partition, writing 05-risks.md and 06-documentation.md into its owned partition directory (05 only in lite mode). TRIGGER WHEN: spawned by /codebase-xray:team-analyze in its second wave.
Agent
Runs Structure Extraction and Interface Analysis over one partition, writing 01-structure.md and 02-interfaces.md into its owned partition directory. TRIGGER WHEN: spawned by /codebase-xray:team-analyze in its first wave. DO NOT TRIGGER WHEN: outside that pipeline; /codebase-xray:analyze extracts structure inline…
Agent
Consolidates per-partition X-ray outputs into the standard 01..07.md layout in the run directory, adding cross-partition sections and a team-mode final report, byte-compatible with a classic single-agent run. TRIGGER WHEN: spawned by /codebase-xray:team-analyze in its consolidation phase. DO NOT TRIGGER WHEN: outside…
Agent
Phase 1b context builder whose output downstream reviewers, doc writers and drift hunters work against. Produces no verdicts of its own. TRIGGER WHEN: the user runs /team-review or /map-codebase, or explicitly asks to map contracts, invariants, domain rules, call graphs, or integration boundaries. DO NOT TRIGGER WHEN…
Command
Run an X-ray: document WHAT, WHY, HOW and CONSEQUENCES into phased files, with concurrent-run support. TRIGGER WHEN: the user asks for a deep analysis of an unfamiliar codebase, pre-review context, or a structure-plus-semantics snapshot. DO NOT TRIGGER WHEN: the user wants human-readable narrative docs (use…
Command
Multi-agent X-ray for large or multi-workspace codebases: splits the project into its natural units, works them in parallel, and publishes one consolidated result set to the .deep-dive/ root. TRIGGER WHEN: the user wants X-ray analysis on a monorepo, or a cross-partition interconnection map produced as part of the…
Skill Claude CodeCodex
X-ray method: mechanical structure extraction fused with semantic reading into a ground-truth account of WHAT, WHY, HOW and CONSEQUENCES. Python, Java, JavaScript, TypeScript, SQL, PL/SQL, Rust. TRIGGER WHEN: encountering an unfamiliar codebase, needing pre-review technical context, before a major refactor, or when…
Plugin Claude Code
Constraint Satisfaction Problems and combinatorial optimization with Google OR-Tools CP-SAT solver.
Agent
Formulate, encode, and deploy discrete decision engines for production use. TRIGGER WHEN: modeling scheduling, routing, assignment, bin-packing, or any constraint satisfaction / combinatorial optimization problem; using Google OR-Tools CP-SAT; needing symmetry breaking, search strategy tuning, or solver performance…
Plugin Claude Code
Evidence-first dependency auditing: runs each ecosystem's real audit tooling for CVEs, outdated packages, license obligations and supply-chain signals, and reports only tool-verified facts under TOOL-REPORTED, INFERRED and UNKNOWN evidence tiers. Obligations-based license analysis instead of a compatibility matrix…