Skill Claude CodeCodex
Use only when the user explicitly asks to be grilled, interviewed, or stress-tested, when /wf routes one genuine human-owned ambiguity, or when a named Wayfinder HITL decision ticket invokes it. Resolves bounded human decisions with evidence, recommendations, traceable records, and no implementation.
Skill Claude CodeCodex
Use when complex comparisons, architectures, processes, decisions, or risk boundaries are easier to understand as a graphic-first, minimal-text, temporary HTML brief.
Skill Claude CodeCodex
Use when work is multi-step, context-heavy, research-heavy, or delegated. Contains bulky context, phases work, bounds retries, delegates independent reasoning, and reserves capacity for verification.
Skill Claude CodeCodex
Use when designing, operating, or verifying encrypted backups and disaster recovery for Hermes state. Combines sanitized Git history, atomic Restic snapshots, WAL-safe SQLite copies, manifest checks, retention gates, and clean-room restore drills.
Skill Claude CodeCodex
Use when Hermes may create, move, clean up, or audit transient and generated files. Keeps artifacts in predictable workspace folders and requires manifests, approval, and rollback planning before cleanup.
Skill Claude CodeCodex
Use when coordinating Hermes Kanban work as either orchestrator or worker. Covers decomposition, ticket lifecycle, worker updates, anti-temptation rules, and handoff discipline.
Skill Claude CodeCodex
Use when the user wants an actionable implementation plan instead of execution. Produces a project-local markdown contract with exact paths, interfaces, tests, constraints, reviewable tasks, and no mutation beyond the plan file.
Skill Claude CodeCodex
Use when the user explicitly asks for a prototype or when a named Wayfinder PROTOTYPE ticket needs runnable logic/UI decision evidence. Builds one throwaway artifact, obtains human reaction, and never promotes it to production automatically.
Skill Claude CodeCodex
Use when authoring, validating, publishing, maintaining, consolidating, or archiving Hermes skills. Covers package structure, provenance, privacy, approval-bound releases, isolated consumer verification, and curator-safe maintenance.
Skill Claude CodeCodex
Use when settled requirements need a clear execution contract. Applies a lightweight in-session specification automatically for medium jobs and a durable traceable draft when explicitly requested or when complex work needs persistent acceptance evidence.
Skill Claude Code
Use when the user explicitly asks to turn an approved specification, plan, or settled contract into agent-sized implementation tickets with requirement coverage and blocking edges. Drafts first; publishes only with separate authority.
Skill Claude CodeCodex
Use for medium-to-large work with multiple material decisions, dependencies, fog, or multi-session coordination. Applies a lightweight in-session route automatically when useful and a durable full Wayfinder package when explicitly invoked or scale requires persistence.
Skill Claude CodeCodex
Use automatically when genuine confusion, vagueness, missing authority, contradictory evidence, or unclear acceptance could change the work. Research discoverable facts first; route a gap resolvable by one human decision to Bounded Grilling, and larger or dependent fog—where one decision would not settle the route—to…
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: