← ClaudeAtlas

scopelisted

Use at the start of any task in a moon monorepo to scope work to the affected project graph — runs `moon query changed-files`/`affected`, dispatches the affected-scout subagent, and returns a structured scope map (affected projects, layers, tasks, downstream blast radius). Prefer this over blindly scanning the repo when working in a repo with a `.moon/` workspace.
g-bastianelli/nuthouse · ★ 1 · AI & Automation · score 70
Install: claude install-skill g-bastianelli/nuthouse
> Workflow kernel: When this skill needs a workflow/profile decision and no valid parent manifest is supplied, use this plugin's install-local `lib/workflow/index.mjs` explicit-skill resolver. Claude hooks are optional accelerators; a missing or failed hook falls back once to that local path. Warden must not be required. When verification is required and Moon Moth is unavailable, use non-empty commands from repository-owned instructions or build metadata, or block completion. # scope > Agent resolution: Before any subagent dispatch, read > `${CLAUDE_PLUGIN_ROOT}/shared/agent-runtime-map.md`; select the active runtime name and follow its spawn rule. > At visible transitions, try to dispatch `warden:voice` with `SUMMARY: <≤15 words, in the user's language>`, `PERSONA_CONTRACT_PATH: ${CLAUDE_PLUGIN_ROOT}/shared/persona-line-contract.md`, and `VOICE_FLAG_PATH: $HOME/.claude/nuthouse/voice.state`. Print the returned `line` only when non-empty. If `warden` is unavailable, errors, returns malformed output, or voice is disabled, print nothing and continue. Never make voice a precondition, never retry, never mention missing `warden`. ## Voice Read `../../persona.md` at the start of this skill. The moon-moth voice is canonical for all output here. Apply it to the wrapper lines around reports; keep the report blocks themselves plain. **Scope:** local to this skill's execution only. Once the final report is printed, revert to the session default voice. This skill is **rigid** — ex