feat(ultraplan-local): M0 — profile foundation, no behaviour change

Introduces a profile-loader infrastructure for runtime-instantiable
ultraplan variants (depth × domain × goal axes). M0 ships only the
`default` profile, which mirrors the current hardcoded Phase 5/9 agent
set — so existing flows are unaffected.

What lands:
- profiles/default.yaml — schema v1, lists current 8 exploration agents
  + 2 review agents, captures today's adversarial regime
- scripts/profile-loader.mjs — null-deps Node loader with limited-subset
  YAML parser, listProfiles(), loadProfile(), validateProfile() that
  cross-checks every referenced agent exists in agents/
- scripts/profile-loader.test.mjs — 26 node:test cases (parser, validation,
  loader, integration with built-in default.yaml)
- commands/ultraplan-local.md — Phase 1 gains a "Resolve the profile"
  step (--profile flag → brief.recommended_profile → default fallback)
  and prints profile + source in the mode report. Phase 5/9 unchanged.
- README.md, CLAUDE.md, marketplace README — documentation of the M0
  foundation, the universal-brief design principle, and the M1/M2/M3
  milestones to come.

M1 (next) wires profile recommendation into ultrabrief Phase 4. M2
ships the additional built-in profiles (quick, bugfix, feature, refactor,
security-deep, research-heavy) and replaces the hardcoded Phase 5 agent
table with profile-driven selection. M3 adds user-extensible profiles.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

README.md

@@ -81,6 +81,14 @@ Five core commands plus an authoring command, one pipeline with clear division o
 
 All artifacts land in one project directory: `.claude/projects/{YYYY-MM-DD}-{slug}/` contains `brief.md`, `research/NN-*.md`, `architecture/` *(v2.2)*, `plan.md`, `sessions/`, and `progress.json`. `--project <dir>` works across `/ultraresearch-local`, `/ultra-cc-architect-local`, `/ultraplan-local`, and `/ultraexecute-local`.
 
+M0 of the runtime-profile work (additive, no behaviour change) introduces `profiles/*.yaml` and `scripts/profile-loader.mjs` — a null-deps Node loader with a limited-subset YAML parser and agent cross-validation (every referenced agent must exist as `agents/<name>.md`).
+
+Phase 1 of `/ultraplan-local` now resolves a profile in the order `--profile flag → brief.recommended_profile → default fallback` and reports `Profile: {name} (source: ...)` in the mode banner. M0 ships only `default.yaml`, which mirrors the current hardcoded Phase 5/9 agent set verbatim — so existing flows are unaffected.
+
+The remaining milestones layer on top: M1 wires profile recommendation into `/ultrabrief-local` Phase 4 (brief recommends a profile, user confirms or overrides). M2 ships additional built-in profiles (`quick`, `bugfix`, `feature`, `refactor`, `security-deep`, `research-heavy`) and replaces the hardcoded Phase 5 agent table with profile-driven selection. M3 adds user-extensible profiles in `.claude/ultraplan-profiles/` and `~/.claude/ultraplan-profiles/`.
+
+The whole design preserves a universal brief: `/ultrabrief-local` asks the same questions regardless of domain, and the profile is a *processing decision* layered on top of that universal data capture. No silent variant routing, no hidden magic — the active profile is always reported and overridable.
+
 v2.4.0 (breaking, default behavior) removes background mode from `/ultraplan-local`, `/ultraresearch-local`, `/ultra-cc-architect-local`, and `/ultrabrief-local` auto-mode. The commands now run foreground in the main context because the harness does not expose the Agent tool to sub-agents — background orchestrators silently degraded the swarm to inline reasoning without external research tools. The `--fg` flag is preserved as a no-op alias for backward compatibility. Source: github.com/anthropics/claude-code/issues/19077.
 
 v2.3 (non-breaking) ships the skill-factory Fase 1 MVP: `/ultra-skill-author-local` plus four supporting agents (1 opus orchestrator + 3 sonnet workers) and `scripts/ngram-overlap.mjs` (pure Node stdlib, word-5-gram containment + longest-run secondary signal, calibrated against three source/draft fixture pairs). Catalog growth is now tractable without touching the architect's hallucination gate. Non-goals stay explicit: no automation, no batch, no decision-layer skills, no remote sources — manual `mv` from `.drafts/` to catalog root is the promotion mechanism. v2.3.1 adds a qualified-slug convention (`<cc_feature>[-<qualifier>]-<layer>.md`) so one feature can host multiple named patterns at different abstraction levels without displacing the baseline — resolved a collision surfaced in v2.3.0 dogfood. v2.3.2 closes the UX gap: `skill-drafter` now reads `{catalog_root}/<slug>.md` before writing and surfaces a collision warning in its confirmation output with a suggested qualified slug, so users see the overwrite risk before running `mv` — not after.