From elixir-phoenix
Audits project health across architecture, performance, security, tests, and dependencies using 5 parallel subagents. Run quarterly, before releases, after refactors, or for onboarding.
How this skill is triggered — by the user, by Claude, or both
Slash command
/elixir-phoenix:auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Comprehensive project-wide health assessment using 5 parallel specialist subagents.
Comprehensive project-wide health assessment using 5 parallel specialist subagents.
/phx:audit # Full audit (default)
/phx:audit --quick # 2-3 minute pulse check
/phx:audit --focus=security # Deep dive single area
/phx:audit --focus=performance
/phx:audit --since abc123 # Incremental audit since commit
/phx:audit --since HEAD~10 # Audit last 10 commits
--quick first to catch compile/test failures before spending tokens on 5 parallel agentsSpawn 5 specialists in parallel using Agent tool:
| Subagent | Focus | Output File |
|---|---|---|
| Architecture Reviewer | Structure quality, coupling, cohesion | arch-review.md |
| Performance Auditor | N+1, indexes, bottlenecks, scalability | perf-audit.md |
| Security Auditor | OWASP scan, auth patterns, secrets | security-audit.md |
| Test Health Auditor | Coverage, quality, flaky tests | test-audit.md |
| Dependency Auditor | Vulnerabilities, outdated, unused | deps-audit.md |
Create Claude Code tasks for real-time progress visibility:
For each auditor:
TaskCreate({subject: "{Area} audit", activeForm: "Auditing {area}..."})
TaskUpdate({taskId, status: "in_progress"})
Then spawn all 5 agents with Agent tool (parallel):
Agent(subagent_type: "general-purpose", prompt: "Architecture audit...", run_in_background: true)
Agent(subagent_type: "general-purpose", prompt: "Performance audit...", run_in_background: true)
Agent(subagent_type: "general-purpose", prompt: "Security audit...", run_in_background: true)
Agent(subagent_type: "general-purpose", prompt: "Test health audit...", run_in_background: true)
Agent(subagent_type: "general-purpose", prompt: "Dependency audit...", run_in_background: true)
Agent prompts must be FOCUSED. Scope each prompt to the relevant directories and patterns. Do NOT give vague prompts like "analyze the codebase."
Output efficiency: Tell each agent: "Report ONLY issues found. Do NOT list clean checks, passing categories, or 'What's Good'. One summary line per clean area suffices."
Wait for ALL auditors to complete. Mark each auditor's task as
completed via TaskUpdate as it finishes. NEVER proceed while
any auditor is still running.
Read reports from .claude/audit/reports/.
After all 5 auditors complete, spawn context-supervisor:
Agent(subagent_type: "context-supervisor", prompt: """
Compress audit findings.
Input: .claude/audit/reports/
Output: .claude/audit/summaries/
Priority: Health scores per category, critical findings
only, cross-category correlations, deduplicate findings
found by 2+ agents.
""")
Read .claude/audit/summaries/consolidated.md for synthesis.
Each category scores 0-100. See ${CLAUDE_SKILL_DIR}/references/scoring-methodology.md.
Write to .claude/audit/summaries/project-health-{date}.md.
Report includes: Executive summary with health score (A-F, numeric/100), per-category score table (Architecture, Performance, Security, Tests, Dependencies), critical issues, top recommendations, and action plan (Immediate/Short-term/Long-term).
--quick)Only run essential checks (~2-3 minutes):
Run mix compile --warnings-as-errors, then mix hex.audit && mix deps.audit,
then mix xref graph --format stats, then mix test --trace 2>&1 | tail -20.
Skip: Full security scan, N+1 analysis, test quality metrics, architecture deep dive.
--focus=area)Deep dive single area with full specialist resources:
| Focus | Subagent | Extra Checks |
|---|---|---|
security | security-analyzer | Full OWASP, sobelow, manual patterns |
performance | (performance subagent) | Profile-level analysis, query explain |
architecture | (arch subagent) | Full xref, coupling matrix, cohesion |
tests | testing-reviewer | Coverage by context, quality metrics |
deps | (deps subagent) | License audit, maintenance status |
--since <commit>)Analyze only changes since a specific commit. Useful for pre-merge checks:
Run git diff --name-only <commit>...HEAD to identify changed files, then run targeted audits on changed files only (skips full project scan).
Combines with other flags: /phx:audit --since HEAD~5 --focus=security
| Command | Scope | Frequency |
|---|---|---|
/phx:review | Changed files (diff) | Every PR |
/phx:audit | Entire project | Quarterly |
/phx:boundaries | Context structure | On-demand |
/phx:verify | Compile/test pass | Anytime |
${CLAUDE_SKILL_DIR}/references/scoring-methodology.md - How scores are calculated${CLAUDE_SKILL_DIR}/references/architecture-checks.md - Detailed architecture criterianpx claudepluginhub oliver-kriska/claude-elixir-phoenix --plugin elixir-phoenixConducts 7-point project health audit covering documentation, test coverage, security, code quality, dependencies, database schema/migrations, and build/CI-CD. Generates scored Markdown report with issues.
Conducts full codebase health audit across architecture, security, code quality, dependencies, test coverage. Produces scored report with letter grades and prioritized remediation. Use for existing codebases or before releases.
Runs an 8-dimension project health audit covering security, dependencies, code quality, architecture, performance, infrastructure, docs, and mesh analytics. Delegates to specialist skills and produces a consolidated health score and action plan.