Skill Claude CodeCodex
Decide retain, equivalent contraction, proven retirement, or unresolved from current FlowGuard DNA.
Executable finite-state models for designing and checking AI-agent workflows, UI flows, and development processes
Skill Claude CodeCodex
Decide retain, equivalent contraction, proven retirement, or unresolved from current FlowGuard DNA.
Skill Claude CodeCodex
Use for external behavior registration, source coverage, one primary owner, change accounting, Primary Path Authority handoff, or broad confidence.
Skill Claude CodeCodex
Use when a FlowGuard model should drive pre-code modules, FunctionBlock/state/field/effect owners, facades, adapters, or validation boundaries.
Skill Claude CodeCodex
Use to generate canonical bad cases, Cartesian combinations, oracles, coverage shards, and receipts from a declared finite boundary, family seed, payload, transition, model mesh, coverage universe, or observed-problem backfeed.
Skill Claude CodeCodex
Order staged work, freshness, sync, release, and process claims.
Skill Claude CodeCodex
Use before non-trivial existing-system work to identify current ownership and duplicate-boundary risk.
Skill Claude CodeCodex
Use when a change adds, removes, renames, migrates, replaces, externalizes, preserves, or audits fields, schema keys, config flags, prompt fields, payload columns, persisted attributes, defaults, aliases, or fallbacks.
Skill Claude CodeCodex
Use for affected topology, partitions, stale child evidence, reattachment, siblings, or mesh closure; count alone is not a trigger.
Skill Claude CodeCodex
Use when post-FlowGuard evidence exposes a missed behavior class or a repair needs generalized closure.
Skill Claude CodeCodex
Align model obligations, CodeContracts, bindings, and tests.
Skill Claude CodeCodex
Use when a locally green FlowGuard model needs topology-grounded future-use hazard review for broad claims, business paths, old/new disposition, side effects, terminals, loops, external boundaries, or parent/child compression.
Skill Claude CodeCodex
Use when an existing large script, module, package, command, public API, facade, config surface, or plugin entrypoint split needs model-derived ownership, dependency, compatibility, parity, and release gates.
Skill Claude CodeCodex
Use when tests/evidence are large, stale, skipped, release-only, or need parent/child ownership.
Skill Claude CodeCodex
Use for UI admission, surfaces, behavior, structure, operability, evidence, or transitions.
Skill Claude CodeCodex
Unified FlowGuard entry for behavior/state models, unclear routes, cross-route work, and kernel gates; use a clear public satellite directly.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: