caee558e79
Add /ultraresearch-local for structured research combining local codebase analysis with external knowledge via parallel agent swarms. Produces research briefs with triangulation, confidence ratings, and source quality assessment. New command: /ultraresearch-local with modes --quick, --local, --external, --fg. New agents: research-orchestrator (opus), docs-researcher, community-researcher, security-researcher, contrarian-researcher, gemini-bridge (all sonnet). New template: research-brief-template.md. Integration: --research flag in /ultraplan-local accepts pre-built research briefs (up to 3), enriches the interview and exploration phases. Planning orchestrator cross-references brief findings during synthesis. Design principle: Context Engineering — right information to right agent at right time. Research briefs are structured artifacts in the pipeline: ultraresearch → brief → ultraplan --research → plan → ultraexecute. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.5 KiB
1.5 KiB
Optimal Setup Example
This example demonstrates a fully-configured Claude Code project that scores A on config-audit's posture assessment.
What's configured
| Feature | File | Gap Check |
|---|---|---|
| Project instructions | CLAUDE.md |
t1_1 |
| Permissions | .claude/settings.json |
t1_2 |
| Hooks (3 events) | hooks/hooks.json |
t1_3, t2_5 |
| Custom commands | .claude/commands/build.md |
t1_4 |
| MCP servers | .mcp.json |
t1_5, t4_1 |
| Multi-scope settings | .claude/settings.local.json |
t2_1 |
| Modular rules | .claude/rules/ |
t2_2 |
| Path-scoped rules | code-style.md, testing.md |
t2_3 |
| Custom agents | .claude/agents/review-agent.md |
t2_6 |
| Model config | settings.json (model key) |
t2_7 |
| Status line | settings.json (statusLine) |
t3_1 |
| Custom keybindings | .claude/keybindings.json |
t3_2 |
| Output style | settings.json (outputStyle) |
t3_3 |
| Worktree config | settings.json (worktree) |
t3_4 |
| Advanced skill frontmatter | build.md (argument-hint) |
t3_5 |
| Agent isolation | review-agent.md (worktree) |
t3_6 |
| Dynamic context | build.md (!git ...) |
t3_7 |
| Auto mode | settings.json (autoMode) |
t3_8 |
| Plugin manifest | .claude-plugin/plugin.json |
t4_2 |
| Agent teams | settings.json (env) |
t4_3 |
| LSP config | .lsp.json |
t4_5 |
How to test
cd examples/optimal-setup
node ../../scanners/posture.mjs .
Expected: A-grade score with high utilization across all tiers.