Agent Claude Code
Use for broad read-only exploration, execution-path tracing, dependency mapping, and locating the authoritative Rust implementation. Returns compact file-grounded evidence rather than raw search output.
AI-Native Formal Specification Language — a bounded model checker (Lark + Z3) built for LLM write/verify/repair loops.
Agent Claude Code
Use for broad read-only exploration, execution-path tracing, dependency mapping, and locating the authoritative Rust implementation. Returns compact file-grounded evidence rather than raw search output.
Agent Claude Code
Use PROACTIVELY after changing Rust FSL syntax, lowering, semantics, CLI commands, public Kernel contracts, or corpus specs. Reports missing coupled code, tests, docs, skills, generated artifacts, and changelog updates. Read-only.
Agent Claude Code
Use PROACTIVELY after changing Rust core/runtime/verifier/solver/refinement semantics. Audits symbolic BMC versus the solver-independent Monitor/BFS, false-negative risk, dependency boundaries, and cross-implementation evidence. Read-only on source; may run focused tests.
Agent Claude Code
Use when Rust, parity, browser, or compatibility test output is verbose or ambiguous. Isolates the first causal failure, reproduces it narrowly, and returns a compact evidence report without editing source.
Agent Claude Code
Use PROACTIVELY after adding or changing a .fsl spec under specs/ or examples/. Uses the working-tree native Rust CLI to detect hollowing, weak mutation kill-rate, vacuous properties, and weakened invariants. Read-only on specs; may run verifier commands.