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>
120 lines
3.7 KiB
Markdown
120 lines
3.7 KiB
Markdown
---
|
|
name: config-audit:posture
|
|
description: Quick configuration health assessment — scorecard with A-F grades
|
|
argument-hint: "[path] [--drift] [--plugin-health]"
|
|
allowed-tools: Read, Write, Glob, Grep, Bash
|
|
model: sonnet
|
|
---
|
|
|
|
# Config-Audit: Health Assessment
|
|
|
|
Quick, deterministic configuration health scorecard. No agents needed — runs all scanners + scoring in one pass.
|
|
|
|
## What the user gets
|
|
|
|
- Health grade (A-F) with plain-language explanation
|
|
- Per-area breakdown for 7 quality areas with grades and actionable notes
|
|
- Opportunity count — how many features could enhance their setup (not a grade)
|
|
- Grade-appropriate next steps
|
|
|
|
## Implementation
|
|
|
|
### Step 1: Determine target
|
|
|
|
Parse `$ARGUMENTS` for a path (default: current working directory). Resolve relative paths.
|
|
|
|
Tell the user:
|
|
|
|
```
|
|
## Configuration Health
|
|
|
|
Running quick assessment{if path != cwd: " on `{path}`"}...
|
|
```
|
|
|
|
### Step 2: Run posture scanner
|
|
|
|
Run silently — all output goes to a file:
|
|
|
|
```bash
|
|
node ${CLAUDE_PLUGIN_ROOT}/scanners/posture.mjs <target-path> --json --output-file /tmp/config-audit-posture-$$.json 2>/dev/null; echo $?
|
|
```
|
|
|
|
If exit code is non-zero, tell the user: "Assessment couldn't complete. Check that the path exists and contains Claude Code configuration files."
|
|
|
|
### Step 3: Read and interpret results
|
|
|
|
Read the JSON output file using the Read tool. Extract:
|
|
|
|
- `overallGrade`, `opportunityCount`
|
|
- `areas[]` — each with `name`, `grade`, `score`, `findingCount`
|
|
|
|
### Step 4: Present the scorecard
|
|
|
|
```markdown
|
|
**Health: {overallGrade}** | {qualityAreaCount} areas scanned
|
|
|
|
{grade-based context — pick ONE:}
|
|
- A: "Your configuration is correct and well-maintained."
|
|
- B: "Solid configuration with minor improvements available."
|
|
- C: "Working configuration with some issues worth addressing."
|
|
- D: "Configuration needs attention in several areas."
|
|
- F: "Significant issues found — addressing these will improve your experience."
|
|
|
|
### Area Scores
|
|
|
|
| Area | Grade | Score | Findings | |
|
|
|------|-------|-------|----------|-|
|
|
{for each area EXCEPT Feature Coverage:}
|
|
| {name} | {grade} | {score}/100 | {findingCount} | {plain-language note: A="Excellent", B="Good", C="Needs work", D/F="Issues found"} |
|
|
|
|
{if opportunityCount > 0:}
|
|
{opportunityCount} feature opportunities available — run `/config-audit feature-gap` for context-aware recommendations.
|
|
|
|
### What's next
|
|
```
|
|
|
|
**Grade A or B:**
|
|
```
|
|
Your configuration health is strong. Re-run after major changes to catch regressions.
|
|
For feature recommendations: `/config-audit feature-gap`
|
|
```
|
|
|
|
**Grade C:**
|
|
```
|
|
Run `/config-audit fix` to auto-fix what's possible, then `/config-audit plan` for a prioritized improvement path.
|
|
```
|
|
|
|
**Grade D or F:**
|
|
```
|
|
Start with `/config-audit fix` — it handles the most impactful issues automatically with backup and rollback.
|
|
Then run `/config-audit plan` for a step-by-step path to a better configuration.
|
|
```
|
|
|
|
### Step 5: Optional sections
|
|
|
|
**If `--drift` flag is present:**
|
|
|
|
Run drift comparison silently:
|
|
```bash
|
|
node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <target-path> 2>/dev/null
|
|
```
|
|
|
|
Read stdout output and append a "Configuration Drift" section showing what changed since the last baseline.
|
|
|
|
**If `--plugin-health` flag is present:**
|
|
|
|
Run plugin health scanner silently:
|
|
```bash
|
|
node ${CLAUDE_PLUGIN_ROOT}/scanners/plugin-health-scanner.mjs <target-path> 2>/dev/null
|
|
```
|
|
|
|
Read stdout output and append a "Plugin Health" section.
|
|
|
|
**If both flags:** Use `scanners/lib/report-generator.mjs` to produce a unified markdown report.
|
|
|
|
### Step 6: Save to session (if active)
|
|
|
|
If a config-audit session exists, save results:
|
|
```bash
|
|
node ${CLAUDE_PLUGIN_ROOT}/scanners/posture.mjs <target-path> --json --output-file ~/.claude/config-audit/sessions/<session-id>/posture.json 2>/dev/null
|
|
```
|